diff options
Diffstat (limited to 'fs')
112 files changed, 2355 insertions, 1273 deletions
@@ -140,6 +140,7 @@ config EXT4DEV_FS tristate "Ext4dev/ext4 extended fs support development (EXPERIMENTAL)" depends on EXPERIMENTAL select JBD2 + select CRC16 help Ext4dev is a predecessor filesystem of the next generation extended fs ext4, based on ext3 filesystem code. It will be @@ -219,7 +220,7 @@ config JBD config JBD_DEBUG bool "JBD (ext3) debugging support" - depends on JBD + depends on JBD && DEBUG_FS help If you are using the ext3 journaled file system (or potentially any other file system/device using JBD), this option allows you to @@ -228,10 +229,10 @@ config JBD_DEBUG debugging output will be turned off. If you select Y here, then you will be able to turn on debugging - with "echo N > /proc/sys/fs/jbd-debug", where N is a number between - 1 and 5, the higher the number, the more debugging output is - generated. To turn debugging off again, do - "echo 0 > /proc/sys/fs/jbd-debug". + with "echo N > /sys/kernel/debug/jbd/jbd-debug", where N is a + number between 1 and 5, the higher the number, the more debugging + output is generated. To turn debugging off again, do + "echo 0 > /sys/kernel/debug/jbd/jbd-debug". config JBD2 tristate @@ -710,18 +710,9 @@ static ssize_t aio_run_iocb(struct kiocb *iocb) /* * Now we are all set to call the retry method in async - * context. By setting this thread's io_wait context - * to point to the wait queue entry inside the currently - * running iocb for the duration of the retry, we ensure - * that async notification wakeups are queued by the - * operation instead of blocking waits, and when notified, - * cause the iocb to be kicked for continuation (through - * the aio_wake_function callback). + * context. */ - BUG_ON(current->io_wait != NULL); - current->io_wait = &iocb->ki_wait; ret = retry(iocb); - current->io_wait = NULL; if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED) { BUG_ON(!list_empty(&iocb->ki_wait.task_list)); @@ -1508,10 +1499,7 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb) * Simply triggers a retry of the operation via kick_iocb. * * This callback is specified in the wait queue entry in - * a kiocb (current->io_wait points to this wait queue - * entry when an aio operation executes; it is used - * instead of a synchronous wait when an i/o blocking - * condition is encountered during aio). + * a kiocb. * * Note: * This routine is executed with the wait queue lock held. @@ -103,12 +103,11 @@ EXPORT_SYMBOL(inode_setattr); int notify_change(struct dentry * dentry, struct iattr * attr) { struct inode *inode = dentry->d_inode; - mode_t mode; + mode_t mode = inode->i_mode; int error; struct timespec now; unsigned int ia_valid = attr->ia_valid; - mode = inode->i_mode; now = current_fs_time(inode->i_sb); attr->ia_ctime = now; @@ -125,18 +124,25 @@ int notify_change(struct dentry * dentry, struct iattr * attr) if (error) return error; } + + /* + * We now pass ATTR_KILL_S*ID to the lower level setattr function so + * that the function has the ability to reinterpret a mode change + * that's due to these bits. This adds an implicit restriction that + * no function will ever call notify_change with both ATTR_MODE and + * ATTR_KILL_S*ID set. + */ + if ((ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) && + (ia_valid & ATTR_MODE)) + BUG(); + if (ia_valid & ATTR_KILL_SUID) { - attr->ia_valid &= ~ATTR_KILL_SUID; if (mode & S_ISUID) { - if (!(ia_valid & ATTR_MODE)) { - ia_valid = attr->ia_valid |= ATTR_MODE; - attr->ia_mode = inode->i_mode; - } - attr->ia_mode &= ~S_ISUID; + ia_valid = attr->ia_valid |= ATTR_MODE; + attr->ia_mode = (inode->i_mode & ~S_ISUID); } } if (ia_valid & ATTR_KILL_SGID) { - attr->ia_valid &= ~ ATTR_KILL_SGID; if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { if (!(ia_valid & ATTR_MODE)) { ia_valid = attr->ia_valid |= ATTR_MODE; @@ -145,7 +151,7 @@ int notify_change(struct dentry * dentry, struct iattr * attr) attr->ia_mode &= ~S_ISGID; } } - if (!attr->ia_valid) + if (!(attr->ia_valid & ~(ATTR_KILL_SUID | ATTR_KILL_SGID))) return 0; if (ia_valid & ATTR_SIZE) diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index e7204d7..45f5992 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -80,7 +80,7 @@ static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid, *uid = current->uid; *gid = current->gid; - *pgrp = process_group(current); + *pgrp = task_pgrp_nr(current); *minproto = *maxproto = AUTOFS_PROTO_VERSION; diff --git a/fs/autofs/root.c b/fs/autofs/root.c index c148953..5efff3c 100644 --- a/fs/autofs/root.c +++ b/fs/autofs/root.c @@ -214,8 +214,8 @@ static struct dentry *autofs_root_lookup(struct inode *dir, struct dentry *dentr oz_mode = autofs_oz_mode(sbi); DPRINTK(("autofs_lookup: pid = %u, pgrp = %u, catatonic = %d, " - "oz_mode = %d\n", pid_nr(task_pid(current)), - process_group(current), sbi->catatonic, + "oz_mode = %d\n", task_pid_nr(current), + task_pgrp_nr(current), sbi->catatonic, oz_mode)); /* @@ -536,7 +536,7 @@ static int autofs_root_ioctl(struct inode *inode, struct file *filp, struct autofs_sb_info *sbi = autofs_sbi(inode->i_sb); void __user *argp = (void __user *)arg; - DPRINTK(("autofs_ioctl: cmd = 0x%08x, arg = 0x%08lx, sbi = %p, pgrp = %u\n",cmd,arg,sbi,process_group(current))); + DPRINTK(("autofs_ioctl: cmd = 0x%08x, arg = 0x%08lx, sbi = %p, pgrp = %u\n",cmd,arg,sbi,task_pgrp_nr(current))); if (_IOC_TYPE(cmd) != _IOC_TYPE(AUTOFS_IOC_FIRST) || _IOC_NR(cmd) - _IOC_NR(AUTOFS_IOC_FIRST) >= AUTOFS_IOC_COUNT) diff --git a/fs/autofs/waitq.c b/fs/autofs/waitq.c index 19a9caf..be46805 100644 --- a/fs/autofs/waitq.c +++ b/fs/autofs/waitq.c @@ -182,7 +182,7 @@ int autofs_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_toke { struct autofs_wait_queue *wq, **wql; - for ( wql = &sbi->queues ; (wq = *wql) != 0 ; wql = &wq->next ) { + for (wql = &sbi->queues; (wq = *wql) != NULL; wql = &wq->next) { if ( wq->wait_queue_token == wait_queue_token ) break; } diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h index d85f42f..2d4ae40 100644 --- a/fs/autofs4/autofs_i.h +++ b/fs/autofs4/autofs_i.h @@ -131,7 +131,7 @@ static inline struct autofs_info *autofs4_dentry_ino(struct dentry *dentry) filesystem without "magic".) */ static inline int autofs4_oz_mode(struct autofs_sb_info *sbi) { - return sbi->catatonic || process_group(current) == sbi->oz_pgrp; + return sbi->catatonic || task_pgrp_nr(current) == sbi->oz_pgrp; } /* Does a dentry have some pending activity? */ diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index cd81f08..7f05d6c 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -226,7 +226,7 @@ static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid, *uid = current->uid; *gid = current->gid; - *pgrp = process_group(current); + *pgrp = task_pgrp_nr(current); *minproto = AUTOFS_MIN_PROTO_VERSION; *maxproto = AUTOFS_MAX_PROTO_VERSION; @@ -323,7 +323,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) sbi->pipe = NULL; sbi->catatonic = 1; sbi->exp_timeout = 0; - sbi->oz_pgrp = process_group(current); + sbi->oz_pgrp = task_pgrp_nr(current); sbi->sb = s; sbi->version = 0; sbi->sub_version = 0; diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index 45ff3d6..2bbcc81 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -582,7 +582,7 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, s oz_mode = autofs4_oz_mode(sbi); DPRINTK("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d", - current->pid, process_group(current), sbi->catatonic, oz_mode); + current->pid, task_pgrp_nr(current), sbi->catatonic, oz_mode); unhashed = autofs4_lookup_unhashed(sbi, dentry->d_parent, &dentry->d_name); if (!unhashed) { @@ -976,7 +976,7 @@ static int autofs4_root_ioctl(struct inode *inode, struct file *filp, void __user *p = (void __user *)arg; DPRINTK("cmd = 0x%08x, arg = 0x%08lx, sbi = %p, pgrp = %u", - cmd,arg,sbi,process_group(current)); + cmd,arg,sbi,task_pgrp_nr(current)); if (_IOC_TYPE(cmd) != _IOC_TYPE(AUTOFS_IOC_FIRST) || _IOC_NR(cmd) - _IOC_NR(AUTOFS_IOC_FIRST) >= AUTOFS_IOC_COUNT) diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index 0d041a9..1fe28e4 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -376,7 +376,7 @@ int autofs4_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_tok struct autofs_wait_queue *wq, **wql; mutex_lock(&sbi->wq_mutex); - for (wql = &sbi->queues ; (wq = *wql) != 0 ; wql = &wq->next) { + for (wql = &sbi->queues; (wq = *wql) != NULL; wql = &wq->next) { if (wq->wait_queue_token == wait_queue_token) break; } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 6e2f3b8..ba8de7c 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1383,10 +1383,10 @@ static void fill_prstatus(struct elf_prstatus *prstatus, prstatus->pr_info.si_signo = prstatus->pr_cursig = signr; prstatus->pr_sigpend = p->pending.signal.sig[0]; prstatus->pr_sighold = p->blocked.sig[0]; - prstatus->pr_pid = p->pid; - prstatus->pr_ppid = p->parent->pid; - prstatus->pr_pgrp = process_group(p); - prstatus->pr_sid = process_session(p); + prstatus->pr_pid = task_pid_vnr(p); + prstatus->pr_ppid = task_pid_vnr(p->parent); + prstatus->pr_pgrp = task_pgrp_vnr(p); + prstatus->pr_sid = task_session_vnr(p); if (thread_group_leader(p)) { /* * This is the record for the group leader. Add in the @@ -1429,10 +1429,10 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, psinfo->pr_psargs[i] = ' '; psinfo->pr_psargs[len] = 0; - psinfo->pr_pid = p->pid; - psinfo->pr_ppid = p->parent->pid; - psinfo->pr_pgrp = process_group(p); - psinfo->pr_sid = process_session(p); + psinfo->pr_pid = task_pid_vnr(p); + psinfo->pr_ppid = task_pid_vnr(p->parent); + psinfo->pr_pgrp = task_pgrp_vnr(p); + psinfo->pr_sid = task_session_vnr(p); i = p->state ? ffz(~p->state) + 1 : 0; psinfo->pr_state = i; diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 033861c..32649f2 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1342,10 +1342,10 @@ static void fill_prstatus(struct elf_prstatus *prstatus, prstatus->pr_info.si_signo = prstatus->pr_cursig = signr; prstatus->pr_sigpend = p->pending.signal.sig[0]; prstatus->pr_sighold = p->blocked.sig[0]; - prstatus->pr_pid = p->pid; - prstatus->pr_ppid = p->parent->pid; - prstatus->pr_pgrp = process_group(p); - prstatus->pr_sid = process_session(p); + prstatus->pr_pid = task_pid_vnr(p); + prstatus->pr_ppid = task_pid_vnr(p->parent); + prstatus->pr_pgrp = task_pgrp_vnr(p); + prstatus->pr_sid = task_session_vnr(p); if (thread_group_leader(p)) { /* * This is the record for the group leader. Add in the @@ -1391,10 +1391,10 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, psinfo->pr_psargs[i] = ' '; psinfo->pr_psargs[len] = 0; - psinfo->pr_pid = p->pid; - psinfo->pr_ppid = p->parent->pid; - psinfo->pr_pgrp = process_group(p); - psinfo->pr_sid = process_session(p); + psinfo->pr_pid = task_pid_vnr(p); + psinfo->pr_ppid = task_pid_vnr(p->parent); + psinfo->pr_pgrp = task_pgrp_vnr(p); + psinfo->pr_sid = task_session_vnr(p); i = p->state ? ffz(~p->state) + 1 : 0; psinfo->pr_state = i; diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES index bed6215..3d41916 100644 --- a/fs/cifs/CHANGES +++ b/fs/cifs/CHANGES @@ -1,3 +1,19 @@ +Version 1.51 +------------ +Fix memory leak in statfs when mounted to very old servers (e.g. +Windows 9x). Add new feature "POSIX open" which allows servers +which support the current POSIX Extensions to provide better semantics +(e.g. delete for open files opened with posix open). Take into +account umask on posix mkdir not just older style mkdir. Add +ability to mount to IPC$ share (which allows CIFS named pipes to be +opened, read and written as if they were files). When 1st tree +connect fails (e.g. due to signing negotiation failure) fix +leak that causes cifsd not to stop and rmmod to fail to cleanup +cifs_request_buffers pool. Fix problem with POSIX Open/Mkdir on +bigendian architectures. Fix possible memory corruption when +EAGAIN returned on kern_recvmsg. Return better error if server +requires packet signing but client has disabled it. + Version 1.50 ------------ Fix NTLMv2 signing. NFS server mounted over cifs works (if cifs mount is @@ -6,7 +22,10 @@ done with "serverino" mount option). Add support for POSIX Unlink Samba supports newer POSIX CIFS Protocol Extensions). Add "nounix" mount option to allow disabling the CIFS Unix Extensions for just that mount. Fix hang on spinlock in find_writable_file (race when -reopening file after session crash). +reopening file after session crash). Byte range unlock request to +windows server could unlock more bytes (on server copy of file) +than intended if start of unlock request is well before start of +a previous byte range lock that we issued. Version 1.49 ------------ diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile index 6ecd9d6..ff6ba8d 100644 --- a/fs/cifs/Makefile +++ b/fs/cifs/Makefile @@ -3,4 +3,4 @@ # obj-$(CONFIG_CIFS) += cifs.o -cifs-objs := cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o inode.o link.o misc.o netmisc.o smbdes.o smbencrypt.o transport.o asn1.o md4.o md5.o cifs_unicode.o nterr.o xattr.o cifsencrypt.o fcntl.o readdir.o ioctl.o sess.o export.o +cifs-objs := cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o inode.o link.o misc.o netmisc.o smbdes.o smbencrypt.o transport.o asn1.o md4.o md5.o cifs_unicode.o nterr.o xattr.o cifsencrypt.o fcntl.o readdir.o ioctl.o sess.o export.o cifsacl.o diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c index f50a88d..2a01f3e 100644 --- a/fs/cifs/asn1.c +++ b/fs/cifs/asn1.c @@ -385,10 +385,9 @@ asn1_oid_decode(struct asn1_ctx *ctx, unsigned long *optr; size = eoc - ctx->pointer + 1; - *oid = kmalloc(size * sizeof (unsigned long), GFP_ATOMIC); - if (*oid == NULL) { + *oid = kmalloc(size * sizeof(unsigned long), GFP_ATOMIC); + if (*oid == NULL) return 0; - } optr = *oid; @@ -581,9 +580,8 @@ decode_negTokenInit(unsigned char *security_blob, int length, return 0; } else if ((cls != ASN1_UNI) || (con != ASN1_CON) || (tag != ASN1_SEQ)) { - cFYI(1, - ("Exit 6 cls = %d con = %d tag = %d end = %p (%d)", - cls, con, tag, end, *end)); + cFYI(1, ("cls = %d con = %d tag = %d end = %p (%d)", + cls, con, tag, end, *end)); } if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) { diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 1bf8cf5..73c4c41 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -209,13 +209,16 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset, i++; tcon = list_entry(tmp, struct cifsTconInfo, cifsConnectionList); dev_type = le32_to_cpu(tcon->fsDevInfo.DeviceType); - length = - sprintf(buf, - "\n%d) %s Uses: %d Type: %s DevInfo: 0x%x " - "Attributes: 0x%x\nPathComponentMax: %d Status: %d", - i, tcon->treeName, - atomic_read(&tcon->useCount), - tcon->nativeFileSystem, + length = sprintf(buf, "\n%d) %s Uses: %d ", i, + tcon->treeName, atomic_read(&tcon->useCount)); + buf += length; + if (tcon->nativeFileSystem) { + length = sprintf(buf, "Type: %s ", + tcon->nativeFileSystem); + buf += length; + } + length = sprintf(buf, "DevInfo: 0x%x Attributes: 0x%x" + "\nPathComponentMax: %d Status: %d", le32_to_cpu(tcon->fsDevInfo.DeviceCharacteristics), le32_to_cpu(tcon->fsAttrInfo.Attributes), le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength), @@ -876,11 +879,16 @@ security_flags_write(struct file *file, const char __user *buffer, if (count < 3) { /* single char or single char followed by null */ c = flags_string[0]; - if (c == '0' || c == 'n' || c == 'N') + if (c == '0' || c == 'n' || c == 'N') { extended_security = CIFSSEC_DEF; /* default */ - else if (c == '1' || c == 'y' || c == 'Y') + return count; + } else if (c == '1' || c == 'y' || c == 'Y') { extended_security = CIFSSEC_MAX; - return count; + return count; + } else if (!isdigit(c)) { + cERROR(1, ("invalid flag %c", c)); + return -EINVAL; + } } /* else we have a number */ diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c new file mode 100644 index 0000000..e8e5635 --- /dev/null +++ b/fs/cifs/cifsacl.c @@ -0,0 +1,333 @@ +/* + * fs/cifs/cifsacl.c + * + * Copyright (C) International Business Machines Corp., 2007 + * Author(s): Steve French (sfrench@us.ibm.com) + * + * Contains the routines for mapping CIFS/NTFS ACLs + * + * This library is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License as published + * by the Free Software Foundation; either version 2.1 of the License, or + * (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See + * the GNU Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public License + * along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/fs.h> +#include "cifspdu.h" +#include "cifsglob.h" +#include "cifsacl.h" +#include "cifsproto.h" +#include "cifs_debug.h" + + +#ifdef CONFIG_CIFS_EXPERIMENTAL + +static struct cifs_wksid wksidarr[NUM_WK_SIDS] = { + {{1, 0, {0, 0, 0, 0, 0, 0}, {0, 0, 0, 0, 0} }, "null user"}, + {{1, 1, {0, 0, 0, 0, 0, 1}, {0, 0, 0, 0, 0} }, "nobody"}, + {{1, 1, {0, 0, 0, 0, 0, 5}, {cpu_to_le32(11), 0, 0, 0, 0} }, "net-users"}, + {{1, 1, {0, 0, 0, 0, 0, 5}, {cpu_to_le32(18), 0, 0, 0, 0} }, "sys"}, + {{1, 2, {0, 0, 0, 0, 0, 5}, {cpu_to_le32(32), cpu_to_le32(544), 0, 0, 0} }, "root"}, + {{1, 2, {0, 0, 0, 0, 0, 5}, {cpu_to_le32(32), cpu_to_le32(545), 0, 0, 0} }, "users"}, + {{1, 2, {0, 0, 0, 0, 0, 5}, {cpu_to_le32(32), cpu_to_le32(546), 0, 0, 0} }, "guest"} +}; + + +/* security id for everyone */ +static const struct cifs_sid sid_everyone = + {1, 1, {0, 0, 0, 0, 0, 0}, {} }; +/* group users */ +static const struct cifs_sid sid_user = + {1, 2 , {0, 0, 0, 0, 0, 5}, {} }; + + +int match_sid(struct cifs_sid *ctsid) +{ + int i, j; + int num_subauth, num_sat, num_saw; + struct cifs_sid *cwsid; + + if (!ctsid) + return (-1); + + for (i = 0; i < NUM_WK_SIDS; ++i) { + cwsid = &(wksidarr[i].cifssid); + + /* compare the revision */ + if (ctsid->revision != cwsid->revision) + continue; + + /* compare all of the six auth values */ + for (j = 0; j < 6; ++j) { + if (ctsid->authority[j] != cwsid->authority[j]) + break; + } + if (j < 6) + continue; /* all of the auth values did not match */ + + /* compare all of the subauth values if any */ + num_sat = ctsid->num_subauth; + num_saw = cwsid->num_subauth; + num_subauth = num_sat < num_saw ? num_sat : num_saw; + if (num_subauth) { + for (j = 0; j < num_subauth; ++j) { + if (ctsid->sub_auth[j] != cwsid->sub_auth[j]) + break; + } + if (j < num_subauth) + continue; /* all sub_auth values do not match */ + } + + cFYI(1, ("matching sid: %s\n", wksidarr[i].sidname)); + return (0); /* sids compare/match */ + } + + cFYI(1, ("No matching sid")); + return (-1); +} + +/* if the two SIDs (roughly equivalent to a UUID for a user or group) are + the same returns 1, if they do not match returns 0 */ +int compare_sids(struct cifs_sid *ctsid, struct cifs_sid *cwsid) +{ + int i; + int num_subauth, num_sat, num_saw; + + if ((!ctsid) || (!cwsid)) + return (0); + + /* compare the revision */ + if (ctsid->revision != cwsid->revision) + return (0); + + /* compare all of the six auth values */ + for (i = 0; i < 6; ++i) { + if (ctsid->authority[i] != cwsid->authority[i]) + return (0); + } + + /* compare all of the subauth values if any */ + num_sat = ctsid->num_subauth; + num_saw = cwsid->num_subauth; + num_subauth = num_sat < num_saw ? num_sat : num_saw; + if (num_subauth) { + for (i = 0; i < num_subauth; ++i) { + if (ctsid->sub_auth[i] != cwsid->sub_auth[i]) + return (0); + } + } + + return (1); /* sids compare/match */ +} + + +static void parse_ace(struct cifs_ace *pace, char *end_of_acl) +{ + int num_subauth; + + /* validate that we do not go past end of acl */ + + /* XXX this if statement can be removed + if (end_of_acl < (char *)pace + sizeof(struct cifs_ace)) { + cERROR(1, ("ACL too small to parse ACE")); + return; + } */ + + num_subauth = pace->num_subauth; + if (num_subauth) { +#ifdef CONFIG_CIFS_DEBUG2 + int i; + cFYI(1, ("ACE revision %d num_subauth %d", + pace->revision, pace->num_subauth)); + for (i = 0; i < num_subauth; ++i) { + cFYI(1, ("ACE sub_auth[%d]: 0x%x", i, + le32_to_cpu(pace->sub_auth[i]))); + } + + /* BB add length check to make sure that we do not have huge + num auths and therefore go off the end */ + + cFYI(1, ("RID %d", le32_to_cpu(pace->sub_auth[num_subauth-1]))); +#endif + } + + return; +} + +static void parse_ntace(struct cifs_ntace *pntace, char *end_of_acl) +{ + /* validate that we do not go past end of acl */ + if (end_of_acl < (char *)pntace + sizeof(struct cifs_ntace)) { + cERROR(1, ("ACL too small to parse NT ACE")); + return; + } + +#ifdef CONFIG_CIFS_DEBUG2 + cFYI(1, ("NTACE type %d flags 0x%x size %d, access Req 0x%x", + pntace->type, pntace->flags, pntace->size, + pntace->access_req)); +#endif + return; +} + + + +static void parse_dacl(struct cifs_acl *pdacl, char *end_of_acl, + struct cifs_sid *pownersid, struct cifs_sid *pgrpsid) +{ + int i; + int num_aces = 0; + int acl_size; + char *acl_base; + struct cifs_ntace **ppntace; + struct cifs_ace **ppace; + + /* BB need to add parm so we can store the SID BB */ + + /* validate that we do not go past end of acl */ + if (end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) { + cERROR(1, ("ACL too small to parse DACL")); + return; + } + +#ifdef CONFIG_CIFS_DEBUG2 + cFYI(1, ("DACL revision %d size %d num aces %d", + le16_to_cpu(pdacl->revision), le16_to_cpu(pdacl->size), + le32_to_cpu(pdacl->num_aces))); +#endif + + acl_base = (char *)pdacl; + acl_size = sizeof(struct cifs_acl); + + num_aces = le32_to_cpu(pdacl->num_aces); + if (num_aces > 0) { + ppntace = kmalloc(num_aces * sizeof(struct cifs_ntace *), + GFP_KERNEL); + ppace = kmalloc(num_aces * sizeof(struct cifs_ace *), + GFP_KERNEL); + +/* cifscred->cecount = pdacl->num_aces; + cifscred->ntaces = kmalloc(num_aces * + sizeof(struct cifs_ntace *), GFP_KERNEL); + cifscred->aces = kmalloc(num_aces * + sizeof(struct cifs_ace *), GFP_KERNEL);*/ + + for (i = 0; i < num_aces; ++i) { + ppntace[i] = (struct cifs_ntace *) + (acl_base + acl_size); + ppace[i] = (struct cifs_ace *) ((char *)ppntace[i] + + sizeof(struct cifs_ntace)); + + parse_ntace(ppntace[i], end_of_acl); + if (end_of_acl < ((char *)ppace[i] + + (le16_to_cpu(ppntace[i]->size) - + sizeof(struct cifs_ntace)))) { + cERROR(1, ("ACL too small to parse ACE")); + break; + } else + parse_ace(ppace[i], end_of_acl); + +/* memcpy((void *)(&(cifscred->ntaces[i])), + (void *)ppntace[i], + sizeof(struct cifs_ntace)); + memcpy((void *)(&(cifscred->aces[i])), + (void *)ppace[i], + sizeof(struct cifs_ace)); */ + + acl_base = (char *)ppntace[i]; + acl_size = le16_to_cpu(ppntace[i]->size); + } + + kfree(ppace); + kfree(ppntace); + } + + return; +} + + +static int parse_sid(struct cifs_sid *psid, char *end_of_acl) +{ + + /* BB need to add parm so we can store the SID BB */ + + /* validate that we do not go past end of acl */ + if (end_of_acl < (char *)psid + sizeof(struct cifs_sid)) { + cERROR(1, ("ACL too small to parse SID")); + return -EINVAL; + } + + if (psid->num_subauth) { +#ifdef CONFIG_CIFS_DEBUG2 + int i; + cFYI(1, ("SID revision %d num_auth %d First subauth 0x%x", + psid->revision, psid->num_subauth, psid->sub_auth[0])); + + for (i = 0; i < psid->num_subauth; i++) { + cFYI(1, ("SID sub_auth[%d]: 0x%x ", i, + le32_to_cpu(psid->sub_auth[i]))); + } + + /* BB add length check to make sure that we do not have huge + num auths and therefore go off the end */ + cFYI(1, ("RID 0x%x", + le32_to_cpu(psid->sub_auth[psid->num_subauth-1]))); +#endif + } + + return 0; +} + + +/* Convert CIFS ACL to POSIX form */ +int parse_sec_desc(struct cifs_ntsd *pntsd, int acl_len) +{ + int rc; + struct cifs_sid *owner_sid_ptr, *group_sid_ptr; + struct cifs_acl *dacl_ptr; /* no need for SACL ptr */ + char *end_of_acl = ((char *)pntsd) + acl_len; + + owner_sid_ptr = (struct cifs_sid *)((char *)pntsd + + le32_to_cpu(pntsd->osidoffset)); + group_sid_ptr = (struct cifs_sid *)((char *)pntsd + + le32_to_cpu(pntsd->gsidoffset)); + dacl_ptr = (struct cifs_acl *)((char *)pntsd + + le32_to_cpu(pntsd->dacloffset)); +#ifdef CONFIG_CIFS_DEBUG2 + cFYI(1, ("revision %d type 0x%x ooffset 0x%x goffset 0x%x " + "sacloffset 0x%x dacloffset 0x%x", + pntsd->revision, pntsd->type, le32_to_cpu(pntsd->osidoffset), + le32_to_cpu(pntsd->gsidoffset), + le32_to_cpu(pntsd->sacloffset), + le32_to_cpu(pntsd->dacloffset))); +#endif + rc = parse_sid(owner_sid_ptr, end_of_acl); + if (rc) + return rc; + + rc = parse_sid(group_sid_ptr, end_of_acl); + if (rc) + return rc; + + parse_dacl(dacl_ptr, end_of_acl, owner_sid_ptr, group_sid_ptr); + +/* cifscred->uid = owner_sid_ptr->rid; + cifscred->gid = group_sid_ptr->rid; + memcpy((void *)(&(cifscred->osid)), (void *)owner_sid_ptr, + sizeof (struct cifs_sid)); + memcpy((void *)(&(cifscred->gsid)), (void *)group_sid_ptr, + sizeof (struct cifs_sid)); */ + + + return (0); +} +#endif /* CONFIG_CIFS_EXPERIMENTAL */ diff --git a/fs/cifs/cifsacl.h b/fs/cifs/cifsacl.h index 5eff35d..420f878 100644 --- a/fs/cifs/cifsacl.h +++ b/fs/cifs/cifsacl.h @@ -1,7 +1,7 @@ /* * fs/cifs/cifsacl.h * - * Copyright (c) International Business Machines Corp., 2005 + * Copyright (c) International Business Machines Corp., 2007 * Author(s): Steve French (sfrench@us.ibm.com) * * This library is free software; you can redistribute it and/or modify @@ -22,17 +22,65 @@ #ifndef _CIFSACL_H #define _CIFSACL_H + +#define NUM_AUTHS 6 /* number of authority fields */ +#define NUM_SUBAUTHS 5 /* number of sub authority fields */ +#define NUM_WK_SIDS 7 /* number of well known sids */ +#define SIDNAMELENGTH 20 /* long enough for the ones we care about */ + +#define READ_BIT 0x4 +#define WRITE_BIT 0x2 +#define EXEC_BIT 0x1 + +#define UBITSHIFT 6 +#define GBITSHIFT 3 + +struct cifs_ntsd { + __le16 revision; /* revision level */ + __le16 type; + __le32 osidoffset; + __le32 gsidoffset; + __le32 sacloffset; + __le32 dacloffset; +} __attribute__((packed)); + struct cifs_sid { __u8 revision; /* revision level */ - __u8 num_subauths; + __u8 num_subauth; + __u8 authority[6]; + __le32 sub_auth[5]; /* sub_auth[num_subauth] */ /* BB FIXME endianness BB */ +} __attribute__((packed)); + +struct cifs_acl { + __le16 revision; /* revision level */ + __le16 size; + __le32 num_aces; +} __attribute__((packed)); + +struct cifs_ntace { /* first part of ACE which contains perms */ + __u8 type; + __u8 flags; + __le16 size; + __le32 access_req; +} __attribute__((packed)); + +struct cifs_ace { /* last part of ACE which includes user info */ + __u8 revision; /* revision level */ + __u8 num_subauth; __u8 authority[6]; - __u32 sub_auth[4]; - /* next sub_auth if any ... */ + __le32 sub_auth[5]; } __attribute__((packed)); -/* everyone */ -/* extern const struct cifs_sid sid_everyone;*/ -/* group users */ -/* extern const struct cifs_sid sid_user;*/ +struct cifs_wksid { + struct cifs_sid cifssid; + char sidname[SIDNAMELENGTH]; +} __attribute__((packed)); + +#ifdef CONFIG_CIFS_EXPERIMENTAL + +extern int match_sid(struct cifs_sid *); +extern int compare_sids(struct cifs_sid *, struct cifs_sid *); + +#endif /* CONFIG_CIFS_EXPERIMENTAL */ #endif /* _CIFSACL_H */ diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 3627229..632070b 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -345,7 +345,7 @@ static int calc_ntlmv2_hash(struct cifsSesInfo *ses, user = kmalloc(2 + (len * 2), GFP_KERNEL); if (user == NULL) goto calc_exit_2; - len = cifs_strtoUCS(user, ses->userName, len, nls_cp); + len = cifs_strtoUCS((__le16 *)user, ses->userName, len, nls_cp); UniStrupr(user); hmac_md5_update((char *)user, 2*len, pctxt); @@ -356,7 +356,8 @@ static int calc_ntlmv2_hash(struct cifsSesInfo *ses, domain = kmalloc(2 + (len * 2), GFP_KERNEL); if (domain == NULL) goto calc_exit_1; - len = cifs_strtoUCS(domain, ses->domainName, len, nls_cp); + len = cifs_strtoUCS((__le16 *)domain, ses->domainName, len, + nls_cp); /* the following line was removed since it didn't work well with lower cased domain name that passed as an option. Maybe converting the domain name earlier makes sense */ diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index ba8f786..a6fbea5 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -49,10 +49,6 @@ static struct quotactl_ops cifs_quotactl_ops; #endif /* QUOTA */ -#ifdef CONFIG_CIFS_EXPERIMENTAL -extern struct export_operations cifs_export_ops; -#endif /* EXPERIMENTAL */ - int cifsFYI = 0; int cifsERROR = 1; int traceSMB = 0; @@ -240,9 +236,9 @@ static int cifs_permission(struct inode *inode, int mask, struct nameidata *nd) cifs_sb = CIFS_SB(inode->i_sb); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) { + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) return 0; - } else /* file mode might have been restricted at mount time + else /* file mode might have been restricted at mount time on the client (above and beyond ACL on servers) for servers which do not support setting and viewing mode bits, so allowing client to check permissions is useful */ @@ -312,15 +308,15 @@ cifs_show_options(struct seq_file *s, struct vfsmount *m) seq_printf(s, ",domain=%s", cifs_sb->tcon->ses->domainName); } + if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID) || + !(cifs_sb->tcon->unix_ext)) + seq_printf(s, ",uid=%d", cifs_sb->mnt_uid); + if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID) || + !(cifs_sb->tcon->unix_ext)) + seq_printf(s, ",gid=%d", cifs_sb->mnt_gid); } if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) seq_printf(s, ",posixpaths"); - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID) || - !(cifs_sb->tcon->unix_ext)) - seq_printf(s, ",uid=%d", cifs_sb->mnt_uid); - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID) || - !(cifs_sb->tcon->unix_ext)) - seq_printf(s, ",gid=%d", cifs_sb->mnt_gid); seq_printf(s, ",rsize=%d", cifs_sb->rsize); seq_printf(s, ",wsize=%d", cifs_sb->wsize); } @@ -346,7 +342,7 @@ int cifs_xquota_set(struct super_block *sb, int quota_type, qid_t qid, if (pTcon) { cFYI(1, ("set type: 0x%x id: %d", quota_type, qid)); } else { - return -EIO; + rc = -EIO; } FreeXid(xid); @@ -716,7 +712,7 @@ static int cifs_init_inodecache(void) { cifs_inode_cachep = kmem_cache_create("cifs_inode_cache", - sizeof (struct cifsInodeInfo), + sizeof(struct cifsInodeInfo), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_MEM_SPREAD), cifs_init_once); @@ -816,8 +812,8 @@ static int cifs_init_mids(void) { cifs_mid_cachep = kmem_cache_create("cifs_mpx_ids", - sizeof (struct mid_q_entry), 0, - SLAB_HWCACHE_ALIGN, NULL); + sizeof(struct mid_q_entry), 0, + SLAB_HWCACHE_ALIGN, NULL); if (cifs_mid_cachep == NULL) return -ENOMEM; @@ -829,8 +825,8 @@ cifs_init_mids(void) } cifs_oplock_cachep = kmem_cache_create("cifs_oplock_structs", - sizeof (struct oplock_q_entry), 0, - SLAB_HWCACHE_ALIGN, NULL); + sizeof(struct oplock_q_entry), 0, + SLAB_HWCACHE_ALIGN, NULL); if (cifs_oplock_cachep == NULL) { mempool_destroy(cifs_mid_poolp); kmem_cache_destroy(cifs_mid_cachep); @@ -882,7 +878,8 @@ static int cifs_oplock_thread(void *dummyarg) the call */ /* mutex_lock(&inode->i_mutex);*/ if (S_ISREG(inode->i_mode)) { - rc = filemap_fdatawrite(inode->i_mapping); + rc = + filemap_fdatawrite(inode->i_mapping); if (CIFS_I(inode)->clientCanCacheRead == 0) { filemap_fdatawait(inode->i_mapping); @@ -907,8 +904,7 @@ static int cifs_oplock_thread(void *dummyarg) 0 /* len */ , 0 /* offset */, 0, 0, LOCKING_ANDX_OPLOCK_RELEASE, 0 /* wait flag */); - cFYI(1, - ("Oplock release rc = %d ", rc)); + cFYI(1, ("Oplock release rc = %d", rc)); } } else spin_unlock(&GlobalMid_Lock); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index a20de77..0a3ee5a 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -1,7 +1,7 @@ /* * fs/cifs/cifsfs.h * - * Copyright (c) International Business Machines Corp., 2002, 2005 + * Copyright (c) International Business Machines Corp., 2002, 2007 * Author(s): Steve French (sfrench@us.ibm.com) * * This library is free software; you can redistribute it and/or modify @@ -99,7 +99,12 @@ extern int cifs_setxattr(struct dentry *, const char *, const void *, size_t, int); extern ssize_t cifs_getxattr(struct dentry *, const char *, void *, size_t); extern ssize_t cifs_listxattr(struct dentry *, char *, size_t); -extern int cifs_ioctl (struct inode *inode, struct file *filep, +extern int cifs_ioctl(struct inode *inode, struct file *filep, unsigned int command, unsigned long arg); -#define CIFS_VERSION "1.50" + +#ifdef CONFIG_CIFS_EXPERIMENTAL +extern struct export_operations cifs_export_ops; +#endif /* EXPERIMENTAL */ + +#define CIFS_VERSION "1.51" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index b98742f..87f51f2 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -19,6 +19,7 @@ #include <linux/in.h> #include <linux/in6.h> #include "cifs_fs_sb.h" +#include "cifsacl.h" /* * The sizes of various internal tables and strings */ @@ -89,7 +90,8 @@ enum statusEnum { }; enum securityEnum { - LANMAN = 0, /* Legacy LANMAN auth */ + PLAINTXT = 0, /* Legacy with Plaintext passwords */ + LANMAN, /* Legacy LANMAN auth */ NTLM, /* Legacy NTLM012 auth with NTLM hash */ NTLMv2, /* Legacy NTLM auth with NTLMv2 hash */ RawNTLMSSP, /* NTLMSSP without SPNEGO */ @@ -115,6 +117,17 @@ struct mac_key { } data; }; +struct cifs_cred { + int uid; + int gid; + int mode; + int cecount; + struct cifs_sid osid; + struct cifs_sid gsid; + struct cifs_ntace *ntaces; + struct cifs_ace *aces; +}; + /* ***************************************************************** * Except the CIFS PDUs themselves all the @@ -279,6 +292,7 @@ struct cifsTconInfo { FILE_SYSTEM_DEVICE_INFO fsDevInfo; FILE_SYSTEM_ATTRIBUTE_INFO fsAttrInfo; /* ok if fs name truncated */ FILE_SYSTEM_UNIX_INFO fsUnixInfo; + unsigned ipc:1; /* set if connection to IPC$ eg for RPC/PIPES */ unsigned retry:1; unsigned nocase:1; unsigned unix_ext:1; /* if off disable Linux extensions to CIFS protocol @@ -329,6 +343,7 @@ struct cifsFileInfo { struct list_head llist; /* list of byte range locks we have. */ unsigned closePend:1; /* file is marked to close */ unsigned invalidHandle:1; /* file closed via session abend */ + unsigned messageMode:1; /* for pipes: message vs byte mode */ atomic_t wrtPending; /* handle in use - defer close */ struct semaphore fh_sem; /* prevents reopen race after dead ses*/ char *search_resume_name; /* BB removeme BB */ @@ -464,6 +479,9 @@ struct dir_notify_req { #ifdef CONFIG_CIFS_WEAK_PW_HASH #define CIFSSEC_MAY_LANMAN 0x00010 #define CIFSSEC_MAY_PLNTXT 0x00020 +#else +#define CIFSSEC_MAY_LANMAN 0 +#define CIFSSEC_MAY_PLNTXT 0 #endif /* weak passwords */ #define CIFSSEC_MAY_SEAL 0x00040 /* not supported yet */ @@ -477,14 +495,23 @@ require use of the stronger protocol */ #ifdef CONFIG_CIFS_WEAK_PW_HASH #define CIFSSEC_MUST_LANMAN 0x10010 #define CIFSSEC_MUST_PLNTXT 0x20020 +#ifdef CONFIG_CIFS_UPCALL +#define CIFSSEC_MASK 0x3F03F /* allows weak security but also krb5 */ +#else #define CIFSSEC_MASK 0x37037 /* current flags supported if weak */ +#endif /* UPCALL */ +#else /* do not allow weak pw hash */ +#ifdef CONFIG_CIFS_UPCALL +#define CIFSSEC_MASK 0x0F00F /* flags supported if no weak allowed */ #else -#define CIFSSEC_MASK 0x07007 /* flags supported if no weak config */ +#define CIFSSEC_MASK 0x07007 /* flags supported if no weak allowed */ +#endif /* UPCALL */ #endif /* WEAK_PW_HASH */ #define CIFSSEC_MUST_SEAL 0x40040 /* not supported yet */ #define CIFSSEC_DEF CIFSSEC_MAY_SIGN | CIFSSEC_MAY_NTLM | CIFSSEC_MAY_NTLMV2 #define CIFSSEC_MAX CIFSSEC_MUST_SIGN | CIFSSEC_MUST_NTLMV2 +#define CIFSSEC_AUTH_MASK (CIFSSEC_MAY_NTLM | CIFSSEC_MAY_NTLMV2 | CIFSSEC_MAY_LANMAN | CIFSSEC_MAY_PLNTXT | CIFSSEC_MAY_KRB5) /* ***************************************************************** * All constants go here diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index 6a2056e..c41ff74 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -215,6 +215,12 @@ /* file_execute, file_read_attributes*/ /* write_dac, and delete. */ +#define FILE_READ_RIGHTS (FILE_READ_DATA | FILE_READ_EA | FILE_READ_ATTRIBUTES) +#define FILE_WRITE_RIGHTS (FILE_WRITE_DATA | FILE_APPEND_DATA \ + | FILE_WRITE_EA | FILE_WRITE_ATTRIBUTES) +#define FILE_EXEC_RIGHTS (FILE_EXECUTE) + + /* * Invalid readdir handle */ @@ -360,10 +366,10 @@ struct smb_hdr { __u8 WordCount; } __attribute__((packed)); /* given a pointer to an smb_hdr retrieve the value of byte count */ -#define BCC(smb_var) ( *(__u16 *)((char *)smb_var + sizeof(struct smb_hdr) + (2* smb_var->WordCount) ) ) -#define BCC_LE(smb_var) ( *(__le16 *)((char *)smb_var + sizeof(struct smb_hdr) + (2* smb_var->WordCount) ) ) +#define BCC(smb_var) ( *(__u16 *)((char *)smb_var + sizeof(struct smb_hdr) + (2 * smb_var->WordCount))) +#define BCC_LE(smb_var) ( *(__le16 *)((char *)smb_var + sizeof(struct smb_hdr) + (2 * smb_var->WordCount))) /* given a pointer to an smb_hdr retrieve the pointer to the byte area */ -#define pByteArea(smb_var) ((unsigned char *)smb_var + sizeof(struct smb_hdr) + (2* smb_var->WordCount) + 2 ) +#define pByteArea(smb_var) ((unsigned char *)smb_var + sizeof(struct smb_hdr) + (2 * smb_var->WordCount) + 2) /* * Computer Name Length (since Netbios name was length 16 with last byte 0x20) @@ -716,6 +722,14 @@ typedef struct smb_com_findclose_req { #define REQ_OPENDIRONLY 0x00000008 #define REQ_EXTENDED_INFO 0x00000010 +/* File type */ +#define DISK_TYPE 0x0000 +#define BYTE_PIPE_TYPE 0x0001 +#define MESSAGE_PIPE_TYPE 0x0002 +#define PRINTER_TYPE 0x0003 +#define COMM_DEV_TYPE 0x0004 +#define UNKNOWN_TYPE 0xFFFF + typedef struct smb_com_open_req { /* also handles create */ struct smb_hdr hdr; /* wct = 24 */ __u8 AndXCommand; diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 04a69da..1a88366 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -50,7 +50,8 @@ extern int SendReceive(const unsigned int /* xid */ , struct cifsSesInfo *, int * /* bytes returned */ , const int long_op); extern int SendReceive2(const unsigned int /* xid */ , struct cifsSesInfo *, struct kvec *, int /* nvec to send */, - int * /* type of buf returned */ , const int long_op); + int * /* type of buf returned */ , const int long_op, + const int logError /* whether to log status code*/ ); extern int SendReceiveBlockingLock(const unsigned int /* xid */ , struct cifsTconInfo *, struct smb_hdr * /* input */ , @@ -65,7 +66,7 @@ extern unsigned int smbCalcSize_LE(struct smb_hdr *ptr); extern int decode_negTokenInit(unsigned char *security_blob, int length, enum securityEnum *secType); extern int cifs_inet_pton(int, char *source, void *dst); -extern int map_smb_to_linux_error(struct smb_hdr *smb); +extern int map_smb_to_linux_error(struct smb_hdr *smb, int logErr); extern void header_assemble(struct smb_hdr *, char /* command */ , const struct cifsTconInfo *, int /* length of fixed section (word count) in two byte units */); @@ -304,12 +305,13 @@ extern int cifs_calculate_mac_key(struct mac_key *key, const char *rn, const char *pass); extern int CalcNTLMv2_partial_mac_key(struct cifsSesInfo *, const struct nls_table *); -extern void CalcNTLMv2_response(const struct cifsSesInfo *, char * ); +extern void CalcNTLMv2_response(const struct cifsSesInfo *, char *); extern void setup_ntlmv2_rsp(struct cifsSesInfo *, char *, const struct nls_table *); #ifdef CONFIG_CIFS_WEAK_PW_HASH extern void calc_lanman_hash(struct cifsSesInfo *ses, char *lnm_session_key); #endif /* CIFS_WEAK_PW_HASH */ +extern int parse_sec_desc(struct cifs_ntsd *, int); extern int CIFSSMBCopy(int xid, struct cifsTconInfo *source_tcon, const char *fromName, diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 8eb102f..f0d9a48 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -34,10 +34,10 @@ #include <asm/uaccess.h> #include "cifspdu.h" #include "cifsglob.h" +#include "cifsacl.h" #include "cifsproto.h" #include "cifs_unicode.h" #include "cifs_debug.h" -#include "cifsacl.h" #ifdef CONFIG_CIFS_POSIX static struct { @@ -94,9 +94,8 @@ static void mark_open_files_invalid(struct cifsTconInfo *pTcon) write_lock(&GlobalSMBSeslock); list_for_each_safe(tmp, tmp1, &pTcon->openFileList) { open_file = list_entry(tmp, struct cifsFileInfo, tlist); - if (open_file) { + if (open_file) open_file->invalidHandle = TRUE; - } } write_unlock(&GlobalSMBSeslock); /* BB Add call to invalidate_inodes(sb) for all superblocks mounted @@ -439,8 +438,13 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses) pSMB->hdr.Mid = GetNextMid(server); pSMB->hdr.Flags2 |= (SMBFLG2_UNICODE | SMBFLG2_ERR_STATUS); + if ((secFlags & CIFSSEC_MUST_KRB5) == CIFSSEC_MUST_KRB5) pSMB->hdr.Flags2 |= SMBFLG2_EXT_SEC; + else if ((secFlags & CIFSSEC_AUTH_MASK) == CIFSSEC_MAY_KRB5) { + cFYI(1, ("Kerberos only mechanism, enable extended security")); + pSMB->hdr.Flags2 |= SMBFLG2_EXT_SEC; + } count = 0; for (i = 0; i < CIFS_NUM_PROT; i++) { @@ -513,7 +517,7 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses) (int)ts.tv_sec, (int)utc.tv_sec, (int)(utc.tv_sec - ts.tv_sec))); val = (int)(utc.tv_sec - ts.tv_sec); - seconds = val < 0 ? -val : val; + seconds = abs(val); result = (seconds / MIN_TZ_ADJ) * MIN_TZ_ADJ; remain = seconds % MIN_TZ_ADJ; if (remain >= (MIN_TZ_ADJ / 2)) @@ -574,7 +578,20 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses) server->secType = NTLM; else if (secFlags & CIFSSEC_MAY_NTLMV2) server->secType = NTLMv2; - /* else krb5 ... any others ... */ + else if (secFlags & CIFSSEC_MAY_KRB5) + server->secType = Kerberos; + else if (secFlags & CIFSSEC_MAY_LANMAN) + server->secType = LANMAN; +/* #ifdef CONFIG_CIFS_EXPERIMENTAL + else if (secFlags & CIFSSEC_MAY_PLNTXT) + server->secType = ?? +#endif */ + else { + rc = -EOPNOTSUPP; + cERROR(1, ("Invalid security type")); + goto neg_err_exit; + } + /* else ... any others ...? */ /* one byte, so no need to convert this or EncryptionKeyLen from little endian */ @@ -604,22 +621,26 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses) if ((pSMBr->hdr.Flags2 & SMBFLG2_EXT_SEC) && (server->capabilities & CAP_EXTENDED_SECURITY)) { count = pSMBr->ByteCount; - if (count < 16) + if (count < 16) { rc = -EIO; - else if (count == 16) { - server->secType = RawNTLMSSP; - if (server->socketUseCount.counter > 1) { - if (memcmp(server->server_GUID, - pSMBr->u.extended_response. - GUID, 16) != 0) { - cFYI(1, ("server UID changed")); - memcpy(server->server_GUID, - pSMBr->u.extended_response.GUID, - 16); - } - } else + goto neg_err_exit; + } + + if (server->socketUseCount.counter > 1) { + if (memcmp(server->server_GUID, + pSMBr->u.extended_response. + GUID, 16) != 0) { + cFYI(1, ("server UID changed")); memcpy(server->server_GUID, - pSMBr->u.extended_response.GUID, 16); + pSMBr->u.extended_response.GUID, + 16); + } + } else + memcpy(server->server_GUID, + pSMBr->u.extended_response.GUID, 16); + + if (count == 16) { + server->secType = RawNTLMSSP; } else { rc = decode_negTokenInit(pSMBr->u.extended_response. SecurityBlob, @@ -642,10 +663,12 @@ signing_check: /* MUST_SIGN already includes the MAY_SIGN FLAG so if this is zero it means that signing is disabled */ cFYI(1, ("Signing disabled")); - if (server->secMode & SECMODE_SIGN_REQUIRED) + if (server->secMode & SECMODE_SIGN_REQUIRED) { cERROR(1, ("Server requires " - "/proc/fs/cifs/PacketSigningEnabled " - "to be on")); + "packet signing to be enabled in " + "/proc/fs/cifs/SecurityFlags.")); + rc = -EOPNOTSUPP; + } server->secMode &= ~(SECMODE_SIGN_ENABLED | SECMODE_SIGN_REQUIRED); } else if ((secFlags & CIFSSEC_MUST_SIGN) == CIFSSEC_MUST_SIGN) { @@ -1052,7 +1075,7 @@ PsxCreat: InformationLevel) - 4; offset = param_offset + params; pdata = (OPEN_PSX_REQ *)(((char *)&pSMB->hdr.Protocol) + offset); - pdata->Level = SMB_QUERY_FILE_UNIX_BASIC; + pdata->Level = cpu_to_le16(SMB_QUERY_FILE_UNIX_BASIC); pdata->Permissions = cpu_to_le64(mode); pdata->PosixOpenFlags = cpu_to_le32(posix_flags); pdata->OpenFlags = cpu_to_le32(*pOplock); @@ -1098,8 +1121,8 @@ PsxCreat: if (cpu_to_le32(FILE_CREATE) == psx_rsp->CreateAction) *pOplock |= CIFS_CREATE_ACTION; /* check to make sure response data is there */ - if (psx_rsp->ReturnedLevel != SMB_QUERY_FILE_UNIX_BASIC) { - pRetData->Type = -1; /* unknown */ + if (psx_rsp->ReturnedLevel != cpu_to_le16(SMB_QUERY_FILE_UNIX_BASIC)) { + pRetData->Type = cpu_to_le32(-1); /* unknown */ #ifdef CONFIG_CIFS_DEBUG2 cFYI(1, ("unknown type")); #endif @@ -1107,12 +1130,12 @@ PsxCreat: if (pSMBr->ByteCount < sizeof(OPEN_PSX_RSP) + sizeof(FILE_UNIX_BASIC_INFO)) { cERROR(1, ("Open response data too small")); - pRetData->Type = -1; + pRetData->Type = cpu_to_le32(-1); goto psx_create_err; } memcpy((char *) pRetData, (char *)psx_rsp + sizeof(OPEN_PSX_RSP), - sizeof (FILE_UNIX_BASIC_INFO)); + sizeof(FILE_UNIX_BASIC_INFO)); } psx_create_err: @@ -1193,9 +1216,9 @@ OldOpenRetry: } if (*pOplock & REQ_OPLOCK) pSMB->OpenFlags = cpu_to_le16(REQ_OPLOCK); - else if (*pOplock & REQ_BATCHOPLOCK) { + else if (*pOplock & REQ_BATCHOPLOCK) pSMB->OpenFlags = cpu_to_le16(REQ_BATCHOPLOCK); - } + pSMB->OpenFlags |= cpu_to_le16(REQ_MORE_INFO); /* BB fixme add conversion for access_flags to bits 0 - 2 of mode */ /* 0 = read @@ -1310,9 +1333,8 @@ openRetry: } if (*pOplock & REQ_OPLOCK) pSMB->OpenFlags = cpu_to_le32(REQ_OPLOCK); - else if (*pOplock & REQ_BATCHOPLOCK) { + else if (*pOplock & REQ_BATCHOPLOCK) pSMB->OpenFlags = cpu_to_le32(REQ_BATCHOPLOCK); - } pSMB->DesiredAccess = cpu_to_le32(access_flags); pSMB->AllocationSize = 0; /* set file as system file if special file such @@ -1424,9 +1446,8 @@ CIFSSMBRead(const int xid, struct cifsTconInfo *tcon, const int netfid, iov[0].iov_base = (char *)pSMB; iov[0].iov_len = pSMB->hdr.smb_buf_length + 4; - rc = SendReceive2(xid, tcon->ses, iov, - 1 /* num iovecs */, - &resp_buf_type, 0); + rc = SendReceive2(xid, tcon->ses, iov, 1 /* num iovecs */, + &resp_buf_type, 0 /* not long op */, 1 /* log err */ ); cifs_stats_inc(&tcon->num_reads); pSMBr = (READ_RSP *)iov[0].iov_base; if (rc) { @@ -1446,11 +1467,11 @@ CIFSSMBRead(const int xid, struct cifsTconInfo *tcon, const int netfid, *nbytes = 0; } else { pReadData = (char *) (&pSMBr->hdr.Protocol) + - le16_to_cpu(pSMBr->DataOffset); -/* if (rc = copy_to_user(buf, pReadData, data_length)) { + le16_to_cpu(pSMBr->DataOffset); +/* if (rc = copy_to_user(buf, pReadData, data_length)) { cERROR(1,("Faulting on read rc = %d",rc)); rc = -EFAULT; - }*/ /* can not use copy_to_user when using page cache*/ + }*/ /* can not use copy_to_user when using page cache*/ if (*buf) memcpy(*buf, pReadData, data_length); } @@ -1645,7 +1666,7 @@ CIFSSMBWrite2(const int xid, struct cifsTconInfo *tcon, rc = SendReceive2(xid, tcon->ses, iov, n_vec + 1, &resp_buf_type, - long_op); + long_op, 0 /* do not log STATUS code */ ); cifs_stats_inc(&tcon->num_writes); if (rc) { cFYI(1, ("Send error Write2 = %d", rc)); @@ -2538,7 +2559,7 @@ validate_ntransact(char *buf, char **ppparm, char **ppdata, cFYI(1, ("data starts after end of smb")); return -EINVAL; } else if (data_count + *ppdata > end_of_smb) { - cFYI(1,("data %p + count %d (%p) ends after end of smb %p start %p", + cFYI(1, ("data %p + count %d (%p) ends after end of smb %p start %p", *ppdata, data_count, (data_count + *ppdata), end_of_smb, pSMBr)); return -EINVAL; @@ -2615,7 +2636,7 @@ CIFSSMBQueryReparseLinkInfo(const int xid, struct cifsTconInfo *tcon, reparse_buf->TargetNameOffset + reparse_buf->TargetNameLen) > end_of_smb) { - cFYI(1,("reparse buf goes beyond SMB")); + cFYI(1, ("reparse buf beyond SMB")); rc = -EIO; goto qreparse_out; } @@ -3042,25 +3063,12 @@ GetExtAttrOut: #endif /* CONFIG_POSIX */ - -/* security id for everyone */ -static const struct cifs_sid sid_everyone = - {1, 1, {0, 0, 0, 0, 0, 0}, {0, 0, 0, 0}}; -/* group users */ -static const struct cifs_sid sid_user = - {1, 2 , {0, 0, 0, 0, 0, 5}, {32, 545, 0, 0}}; - -/* Convert CIFS ACL to POSIX form */ -static int parse_sec_desc(struct cifs_sid *psec_desc, int acl_len) -{ - return 0; -} - +#ifdef CONFIG_CIFS_EXPERIMENTAL /* Get Security Descriptor (by handle) from remote server for a file or dir */ int CIFSSMBGetCIFSACL(const int xid, struct cifsTconInfo *tcon, __u16 fid, /* BB fix up return info */ char *acl_inf, const int buflen, - const int acl_type /* ACCESS/DEFAULT not sure implication */) + const int acl_type) { int rc = 0; int buf_type = 0; @@ -3085,12 +3093,13 @@ CIFSSMBGetCIFSACL(const int xid, struct cifsTconInfo *tcon, __u16 fid, iov[0].iov_base = (char *)pSMB; iov[0].iov_len = pSMB->hdr.smb_buf_length + 4; - rc = SendReceive2(xid, tcon->ses, iov, 1 /* num iovec */, &buf_type, 0); + rc = SendReceive2(xid, tcon->ses, iov, 1 /* num iovec */, &buf_type, + 0 /* not long op */, 0 /* do not log STATUS codes */ ); cifs_stats_inc(&tcon->num_acl_get); if (rc) { cFYI(1, ("Send error in QuerySecDesc = %d", rc)); } else { /* decode response */ - struct cifs_sid *psec_desc; + struct cifs_ntsd *psec_desc; __le32 * parm; int parm_len; int data_len; @@ -3105,8 +3114,7 @@ CIFSSMBGetCIFSACL(const int xid, struct cifsTconInfo *tcon, __u16 fid, goto qsec_out; pSMBr = (struct smb_com_ntransact_rsp *)iov[0].iov_base; - cERROR(1, ("smb %p parm %p data %p", - pSMBr, parm, psec_desc)); /* BB removeme BB */ + cFYI(1, ("smb %p parm %p data %p", pSMBr, parm, psec_desc)); if (le32_to_cpu(pSMBr->ParameterCount) != 4) { rc = -EIO; /* bad smb */ @@ -3115,7 +3123,7 @@ CIFSSMBGetCIFSACL(const int xid, struct cifsTconInfo *tcon, __u16 fid, /* BB check that data area is minimum length and as big as acl_len */ - acl_len = le32_to_cpu(*(__le32 *)parm); + acl_len = le32_to_cpu(*parm); /* BB check if (acl_len > bufsize) */ parse_sec_desc(psec_desc, acl_len); @@ -3128,6 +3136,7 @@ qsec_out: /* cifs_small_buf_release(pSMB); */ /* Freed earlier now in SendReceive2 */ return rc; } +#endif /* CONFIG_CIFS_EXPERIMENTAL */ /* Legacy Query Path Information call for lookup to old servers such as Win9x/WinME */ @@ -3363,6 +3372,9 @@ UnixQPathInfoRetry: rc = validate_t2((struct smb_t2_rsp *)pSMBr); if (rc || (pSMBr->ByteCount < sizeof(FILE_UNIX_BASIC_INFO))) { + cERROR(1, ("Malformed FILE_UNIX_BASIC_INFO response.\n" + "Unix Extensions can be disabled on mount " + "by specifying the nosfu mount option.")); rc = -EIO; /* bad smb */ } else { __u16 data_offset = le16_to_cpu(pSMBr->t2.DataOffset); @@ -3883,12 +3895,10 @@ getDFSRetry: pSMB->hdr.Mid = GetNextMid(ses->server); pSMB->hdr.Tid = ses->ipc_tid; pSMB->hdr.Uid = ses->Suid; - if (ses->capabilities & CAP_STATUS32) { + if (ses->capabilities & CAP_STATUS32) pSMB->hdr.Flags2 |= SMBFLG2_ERR_STATUS; - } - if (ses->capabilities & CAP_DFS) { + if (ses->capabilities & CAP_DFS) pSMB->hdr.Flags2 |= SMBFLG2_DFS; - } if (ses->capabilities & CAP_UNICODE) { pSMB->hdr.Flags2 |= SMBFLG2_UNICODE; @@ -4060,10 +4070,6 @@ oldQFSInfoRetry: (void **) &pSMBr); if (rc) return rc; - rc = smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB, - (void **) &pSMBr); - if (rc) - return rc; params = 2; /* level */ pSMB->TotalDataCount = 0; @@ -4265,7 +4271,7 @@ QFSAttributeRetry: *) (((char *) &pSMBr->hdr.Protocol) + data_offset); memcpy(&tcon->fsAttrInfo, response_data, - sizeof (FILE_SYSTEM_ATTRIBUTE_INFO)); + sizeof(FILE_SYSTEM_ATTRIBUTE_INFO)); } } cifs_buf_release(pSMB); @@ -4334,7 +4340,7 @@ QFSDeviceRetry: (((char *) &pSMBr->hdr.Protocol) + data_offset); memcpy(&tcon->fsDevInfo, response_data, - sizeof (FILE_SYSTEM_DEVICE_INFO)); + sizeof(FILE_SYSTEM_DEVICE_INFO)); } } cifs_buf_release(pSMB); @@ -4402,7 +4408,7 @@ QFSUnixRetry: *) (((char *) &pSMBr->hdr.Protocol) + data_offset); memcpy(&tcon->fsUnixInfo, response_data, - sizeof (FILE_SYSTEM_UNIX_INFO)); + sizeof(FILE_SYSTEM_UNIX_INFO)); } } cifs_buf_release(pSMB); @@ -4612,7 +4618,7 @@ SetEOFRetry: strncpy(pSMB->FileName, fileName, name_len); } params = 6 + name_len; - data_count = sizeof (struct file_end_of_file_info); + data_count = sizeof(struct file_end_of_file_info); pSMB->MaxParameterCount = cpu_to_le16(2); pSMB->MaxDataCount = cpu_to_le16(4100); pSMB->MaxSetupCount = 0; @@ -4800,7 +4806,7 @@ CIFSSMBSetFileTimes(const int xid, struct cifsTconInfo *tcon, data_offset = (char *) (&pSMB->hdr.Protocol) + offset; - count = sizeof (FILE_BASIC_INFO); + count = sizeof(FILE_BASIC_INFO); pSMB->MaxParameterCount = cpu_to_le16(2); pSMB->MaxDataCount = cpu_to_le16(1000); /* BB find max SMB PDU from sess */ pSMB->SetupCount = 1; @@ -4871,7 +4877,7 @@ SetTimesRetry: } params = 6 + name_len; - count = sizeof (FILE_BASIC_INFO); + count = sizeof(FILE_BASIC_INFO); pSMB->MaxParameterCount = cpu_to_le16(2); pSMB->MaxDataCount = cpu_to_le16(1000); /* BB find exact max SMB PDU from sess structure BB */ pSMB->MaxSetupCount = 0; @@ -4900,7 +4906,7 @@ SetTimesRetry: pSMB->InformationLevel = cpu_to_le16(SMB_SET_FILE_BASIC_INFO); pSMB->Reserved4 = 0; pSMB->hdr.smb_buf_length += byte_count; - memcpy(data_offset, data, sizeof (FILE_BASIC_INFO)); + memcpy(data_offset, data, sizeof(FILE_BASIC_INFO)); pSMB->ByteCount = cpu_to_le16(byte_count); rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, (struct smb_hdr *) pSMBr, &bytes_returned, 0); @@ -5003,7 +5009,7 @@ setPermsRetry: } params = 6 + name_len; - count = sizeof (FILE_UNIX_BASIC_INFO); + count = sizeof(FILE_UNIX_BASIC_INFO); pSMB->MaxParameterCount = cpu_to_le16(2); pSMB->MaxDataCount = cpu_to_le16(1000); /* BB find exact max SMB PDU from sess structure BB */ pSMB->MaxSetupCount = 0; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 4af3588..19ee11f 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -124,7 +124,7 @@ cifs_reconnect(struct TCP_Server_Info *server) struct mid_q_entry *mid_entry; spin_lock(&GlobalMid_Lock); - if ( kthread_should_stop() ) { + if (kthread_should_stop()) { /* the demux thread will exit normally next time through the loop */ spin_unlock(&GlobalMid_Lock); @@ -151,9 +151,8 @@ cifs_reconnect(struct TCP_Server_Info *server) } list_for_each(tmp, &GlobalTreeConnectionList) { tcon = list_entry(tmp, struct cifsTconInfo, cifsConnectionList); - if ((tcon) && (tcon->ses) && (tcon->ses->server == server)) { + if ((tcon) && (tcon->ses) && (tcon->ses->server == server)) tcon->tidStatus = CifsNeedReconnect; - } } read_unlock(&GlobalSMBSeslock); /* do not want to be sending data on a socket we are freeing */ @@ -187,7 +186,7 @@ cifs_reconnect(struct TCP_Server_Info *server) spin_unlock(&GlobalMid_Lock); up(&server->tcpSem); - while ( (!kthread_should_stop()) && (server->tcpStatus != CifsGood)) { + while ((!kthread_should_stop()) && (server->tcpStatus != CifsGood)) { try_to_freeze(); if (server->protocolType == IPV6) { rc = ipv6_connect(&server->addr.sockAddr6, @@ -204,7 +203,7 @@ cifs_reconnect(struct TCP_Server_Info *server) } else { atomic_inc(&tcpSesReconnectCount); spin_lock(&GlobalMid_Lock); - if ( !kthread_should_stop() ) + if (!kthread_should_stop()) server->tcpStatus = CifsGood; server->sequence_number = 0; spin_unlock(&GlobalMid_Lock); @@ -352,17 +351,15 @@ cifs_demultiplex_thread(struct TCP_Server_Info *server) current->flags |= PF_MEMALLOC; server->tsk = current; /* save process info to wake at shutdown */ - cFYI(1, ("Demultiplex PID: %d", current->pid)); + cFYI(1, ("Demultiplex PID: %d", task_pid_nr(current))); write_lock(&GlobalSMBSeslock); atomic_inc(&tcpSesAllocCount); length = tcpSesAllocCount.counter; write_unlock(&GlobalSMBSeslock); complete(&cifsd_complete); - if (length > 1) { - mempool_resize(cifs_req_poolp, - length + cifs_min_rcv, - GFP_KERNEL); - } + if (length > 1) + mempool_resize(cifs_req_poolp, length + cifs_min_rcv, + GFP_KERNEL); set_freezable(); while (!kthread_should_stop()) { @@ -378,7 +375,7 @@ cifs_demultiplex_thread(struct TCP_Server_Info *server) } } else if (isLargeBuf) { /* we are reusing a dirty large buf, clear its start */ - memset(bigbuf, 0, sizeof (struct smb_hdr)); + memset(bigbuf, 0, sizeof(struct smb_hdr)); } if (smallbuf == NULL) { @@ -391,7 +388,7 @@ cifs_demultiplex_thread(struct TCP_Server_Info *server) } /* beginning of smb buffer is cleared in our buf_get */ } else /* if existing small buf clear beginning */ - memset(smallbuf, 0, sizeof (struct smb_hdr)); + memset(smallbuf, 0, sizeof(struct smb_hdr)); isLargeBuf = FALSE; isMultiRsp = FALSE; @@ -400,11 +397,13 @@ cifs_demultiplex_thread(struct TCP_Server_Info *server) iov.iov_len = 4; smb_msg.msg_control = NULL; smb_msg.msg_controllen = 0; + pdu_length = 4; /* enough to get RFC1001 header */ +incomplete_rcv: length = kernel_recvmsg(csocket, &smb_msg, - &iov, 1, 4, 0 /* BB see socket.h flags */); + &iov, 1, pdu_length, 0 /* BB other flags? */); - if ( kthread_should_stop() ) { + if (kthread_should_stop()) { break; } else if (server->tcpStatus == CifsNeedReconnect) { cFYI(1, ("Reconnect after server stopped responding")); @@ -416,7 +415,10 @@ cifs_demultiplex_thread(struct TCP_Server_Info *server) msleep(1); /* minimum sleep to prevent looping allowing socket to clear and app threads to set tcpStatus CifsNeedReconnect if server hung */ - continue; + if (pdu_length < 4) + goto incomplete_rcv; + else + continue; } else if (length <= 0) { if (server->tcpStatus == CifsNew) { cFYI(1, ("tcp session abend after SMBnegprot")); @@ -437,13 +439,11 @@ cifs_demultiplex_thread(struct TCP_Server_Info *server) wake_up(&server->response_q); continue; } else if (length < 4) { - cFYI(1, - ("Frame under four bytes received (%d bytes long)", + cFYI(1, ("less than four bytes received (%d bytes)", length)); - cifs_reconnect(server); - csocket = server->ssocket; - wake_up(&server->response_q); - continue; + pdu_length -= length; + msleep(1); + goto incomplete_rcv; } /* The right amount was read from socket - 4 bytes */ @@ -504,7 +504,7 @@ cifs_demultiplex_thread(struct TCP_Server_Info *server) /* else we have an SMB response */ if ((pdu_length > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) || - (pdu_length < sizeof (struct smb_hdr) - 1 - 4)) { + (pdu_length < sizeof(struct smb_hdr) - 1 - 4)) { cERROR(1, ("Invalid size SMB length %d pdu_length %d", length, pdu_length+4)); cifs_reconnect(server); @@ -528,7 +528,7 @@ cifs_demultiplex_thread(struct TCP_Server_Info *server) total_read += length) { length = kernel_recvmsg(csocket, &smb_msg, &iov, 1, pdu_length - total_read, 0); - if ( kthread_should_stop() || + if (kthread_should_stop() || (length == -EINTR)) { /* then will exit */ reconnect = 2; @@ -546,6 +546,7 @@ cifs_demultiplex_thread(struct TCP_Server_Info *server) allowing socket to clear and app threads to set tcpStatus CifsNeedReconnect if server hung*/ + length = 0; continue; } else if (length <= 0) { cERROR(1, ("Received no data, expecting %d", @@ -631,9 +632,9 @@ multi_t2_fnd: /* Was previous buf put in mpx struct for multi-rsp? */ if (!isMultiRsp) { /* smb buffer will be freed by user thread */ - if (isLargeBuf) { + if (isLargeBuf) bigbuf = NULL; - } else + else smallbuf = NULL; } wake_up_process(task_to_wake); @@ -676,9 +677,8 @@ multi_t2_fnd: server->ssocket = NULL; } /* buffer usuallly freed in free_mid - need to free it here on exit */ - if (bigbuf != NULL) - cifs_buf_release(bigbuf); - if (smallbuf != NULL) + cifs_buf_release(bigbuf); + if (smallbuf) /* no sense logging a debug message if NULL */ cifs_small_buf_release(smallbuf); read_lock(&GlobalSMBSeslock); @@ -702,9 +702,8 @@ multi_t2_fnd: list_for_each(tmp, &GlobalSMBSessionList) { ses = list_entry(tmp, struct cifsSesInfo, cifsSessionList); - if (ses->server == server) { + if (ses->server == server) ses->status = CifsExiting; - } } spin_lock(&GlobalMid_Lock); @@ -714,9 +713,8 @@ multi_t2_fnd: cFYI(1, ("Clearing Mid 0x%x - waking up ", mid_entry->mid)); task_to_wake = mid_entry->tsk; - if (task_to_wake) { + if (task_to_wake) wake_up_process(task_to_wake); - } } } spin_unlock(&GlobalMid_Lock); @@ -749,18 +747,15 @@ multi_t2_fnd: list_for_each(tmp, &GlobalSMBSessionList) { ses = list_entry(tmp, struct cifsSesInfo, cifsSessionList); - if (ses->server == server) { + if (ses->server == server) ses->server = NULL; - } } write_unlock(&GlobalSMBSeslock); kfree(server); - if (length > 0) { - mempool_resize(cifs_req_poolp, - length + cifs_min_rcv, - GFP_KERNEL); - } + if (length > 0) + mempool_resize(cifs_req_poolp, length + cifs_min_rcv, + GFP_KERNEL); return 0; } @@ -1477,7 +1472,7 @@ ipv4_connect(struct sockaddr_in *psin_server, struct socket **csocket, if (psin_server->sin_port) { /* user overrode default port */ rc = (*csocket)->ops->connect(*csocket, (struct sockaddr *) psin_server, - sizeof (struct sockaddr_in), 0); + sizeof(struct sockaddr_in), 0); if (rc >= 0) connected = 1; } @@ -1493,7 +1488,7 @@ ipv4_connect(struct sockaddr_in *psin_server, struct socket **csocket, rc = (*csocket)->ops->connect(*csocket, (struct sockaddr *) psin_server, - sizeof (struct sockaddr_in), 0); + sizeof(struct sockaddr_in), 0); if (rc >= 0) connected = 1; } @@ -1502,7 +1497,7 @@ ipv4_connect(struct sockaddr_in *psin_server, struct socket **csocket, psin_server->sin_port = htons(RFC1001_PORT); rc = (*csocket)->ops->connect(*csocket, (struct sockaddr *) psin_server, - sizeof (struct sockaddr_in), 0); + sizeof(struct sockaddr_in), 0); if (rc >= 0) connected = 1; } @@ -1610,7 +1605,7 @@ ipv6_connect(struct sockaddr_in6 *psin_server, struct socket **csocket) if (psin_server->sin6_port) { /* user overrode default port */ rc = (*csocket)->ops->connect(*csocket, (struct sockaddr *) psin_server, - sizeof (struct sockaddr_in6), 0); + sizeof(struct sockaddr_in6), 0); if (rc >= 0) connected = 1; } @@ -1626,7 +1621,7 @@ ipv6_connect(struct sockaddr_in6 *psin_server, struct socket **csocket) rc = (*csocket)->ops->connect(*csocket, (struct sockaddr *) psin_server, - sizeof (struct sockaddr_in6), 0); + sizeof(struct sockaddr_in6), 0); if (rc >= 0) connected = 1; } @@ -1634,7 +1629,7 @@ ipv6_connect(struct sockaddr_in6 *psin_server, struct socket **csocket) if (!connected) { psin_server->sin6_port = htons(RFC1001_PORT); rc = (*csocket)->ops->connect(*csocket, (struct sockaddr *) - psin_server, sizeof (struct sockaddr_in6), 0); + psin_server, sizeof(struct sockaddr_in6), 0); if (rc >= 0) connected = 1; } @@ -1750,7 +1745,16 @@ void reset_cifs_unix_caps(int xid, struct cifsTconInfo *tcon, cFYI(1, ("very large write cap")); #endif /* CIFS_DEBUG2 */ if (CIFSSMBSetFSUnixInfo(xid, tcon, cap)) { - cFYI(1, ("setting capabilities failed")); + if (vol_info == NULL) { + cFYI(1, ("resetting capabilities failed")); + } else + cERROR(1, ("Negotiating Unix capabilities " + "with the server failed. Consider " + "mounting with the Unix Extensions\n" + "disabled, if problems are found, " + "by specifying the nounix mount " + "option.")); + } } } @@ -1909,8 +1913,8 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, return rc; } - srvTcp = kmalloc(sizeof (struct TCP_Server_Info), GFP_KERNEL); - if (srvTcp == NULL) { + srvTcp = kzalloc(sizeof(struct TCP_Server_Info), GFP_KERNEL); + if (!srvTcp) { rc = -ENOMEM; sock_release(csocket); kfree(volume_info.UNC); @@ -1919,9 +1923,8 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, FreeXid(xid); return rc; } else { - memset(srvTcp, 0, sizeof (struct TCP_Server_Info)); memcpy(&srvTcp->addr.sockAddr, &sin_server, - sizeof (struct sockaddr_in)); + sizeof(struct sockaddr_in)); atomic_set(&srvTcp->inFlight, 0); /* BB Add code for ipv6 case too */ srvTcp->ssocket = csocket; @@ -2173,8 +2176,18 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, if (tsk) kthread_stop(tsk); } - } else + } else { cFYI(1, ("No session or bad tcon")); + if ((pSesInfo->server) && + (pSesInfo->server->tsk)) { + struct task_struct *tsk; + force_sig(SIGKILL, + pSesInfo->server->tsk); + tsk = pSesInfo->server->tsk; + if (tsk) + kthread_stop(tsk); + } + } sesInfoFree(pSesInfo); /* pSesInfo = NULL; */ } @@ -2185,8 +2198,10 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, tcon->ses = pSesInfo; /* do not care if following two calls succeed - informational */ - CIFSSMBQFSDeviceInfo(xid, tcon); - CIFSSMBQFSAttributeInfo(xid, tcon); + if (!tcon->ipc) { + CIFSSMBQFSDeviceInfo(xid, tcon); + CIFSSMBQFSAttributeInfo(xid, tcon); + } /* tell server which Unix caps we support */ if (tcon->ses->capabilities & CAP_UNIX) @@ -2526,8 +2541,7 @@ CIFSSessSetup(unsigned int xid, struct cifsSesInfo *ses, sesssetup_nomem: /* do not return an error on nomem for the info strings, since that could make reconnection harder, and reconnection might be needed to free memory */ - if (smb_buffer) - cifs_buf_release(smb_buffer); + cifs_buf_release(smb_buffer); return rc; } @@ -2547,7 +2561,7 @@ CIFSNTLMSSPNegotiateSessSetup(unsigned int xid, int remaining_words = 0; int bytes_returned = 0; int len; - int SecurityBlobLength = sizeof (NEGOTIATE_MESSAGE); + int SecurityBlobLength = sizeof(NEGOTIATE_MESSAGE); PNEGOTIATE_MESSAGE SecurityBlob; PCHALLENGE_MESSAGE SecurityBlob2; __u32 negotiate_flags, capabilities; @@ -2865,15 +2879,14 @@ CIFSNTLMSSPNegotiateSessSetup(unsigned int xid, rc = -EIO; } - if (smb_buffer) - cifs_buf_release(smb_buffer); + cifs_buf_release(smb_buffer); return rc; } static int CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, - char *ntlm_session_key, int ntlmv2_flag, - const struct nls_table *nls_codepage) + char *ntlm_session_key, int ntlmv2_flag, + const struct nls_table *nls_codepage) { struct smb_hdr *smb_buffer; struct smb_hdr *smb_buffer_response; @@ -2886,7 +2899,7 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, int remaining_words = 0; int bytes_returned = 0; int len; - int SecurityBlobLength = sizeof (AUTHENTICATE_MESSAGE); + int SecurityBlobLength = sizeof(AUTHENTICATE_MESSAGE); PAUTHENTICATE_MESSAGE SecurityBlob; __u32 negotiate_flags, capabilities; __u16 count; @@ -2901,8 +2914,8 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, return -ENOMEM; } smb_buffer_response = smb_buffer; - pSMB = (SESSION_SETUP_ANDX *) smb_buffer; - pSMBr = (SESSION_SETUP_ANDX *) smb_buffer_response; + pSMB = (SESSION_SETUP_ANDX *)smb_buffer; + pSMBr = (SESSION_SETUP_ANDX *)smb_buffer_response; /* send SMBsessionSetup here */ header_assemble(smb_buffer, SMB_COM_SESSION_SETUP_ANDX, @@ -2921,7 +2934,7 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, smb_buffer->Flags2 |= SMBFLG2_SECURITY_SIGNATURE; capabilities = CAP_LARGE_FILES | CAP_NT_SMBS | CAP_LEVEL_II_OPLOCKS | - CAP_EXTENDED_SECURITY; + CAP_EXTENDED_SECURITY; if (ses->capabilities & CAP_UNICODE) { smb_buffer->Flags2 |= SMBFLG2_UNICODE; capabilities |= CAP_UNICODE; @@ -2936,15 +2949,14 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, } pSMB->req.Capabilities = cpu_to_le32(capabilities); - bcc_ptr = (char *) &pSMB->req.SecurityBlob; - SecurityBlob = (PAUTHENTICATE_MESSAGE) bcc_ptr; + bcc_ptr = (char *)&pSMB->req.SecurityBlob; + SecurityBlob = (PAUTHENTICATE_MESSAGE)bcc_ptr; strncpy(SecurityBlob->Signature, NTLMSSP_SIGNATURE, 8); SecurityBlob->MessageType = NtLmAuthenticate; bcc_ptr += SecurityBlobLength; - negotiate_flags = - NTLMSSP_NEGOTIATE_UNICODE | NTLMSSP_REQUEST_TARGET | - NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_TARGET_INFO | - 0x80000000 | NTLMSSP_NEGOTIATE_128; + negotiate_flags = NTLMSSP_NEGOTIATE_UNICODE | NTLMSSP_REQUEST_TARGET | + NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_TARGET_INFO | + 0x80000000 | NTLMSSP_NEGOTIATE_128; if (sign_CIFS_PDUs) negotiate_flags |= /* NTLMSSP_NEGOTIATE_ALWAYS_SIGN |*/ NTLMSSP_NEGOTIATE_SIGN; if (ntlmv2_flag) @@ -2979,36 +2991,32 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, SecurityBlob->DomainName.Length = 0; SecurityBlob->DomainName.MaximumLength = 0; } else { - __u16 len = - cifs_strtoUCS((__le16 *) bcc_ptr, domain, 64, + __u16 ln = cifs_strtoUCS((__le16 *) bcc_ptr, domain, 64, nls_codepage); - len *= 2; + ln *= 2; SecurityBlob->DomainName.MaximumLength = - cpu_to_le16(len); + cpu_to_le16(ln); SecurityBlob->DomainName.Buffer = cpu_to_le32(SecurityBlobLength); - bcc_ptr += len; - SecurityBlobLength += len; - SecurityBlob->DomainName.Length = - cpu_to_le16(len); + bcc_ptr += ln; + SecurityBlobLength += ln; + SecurityBlob->DomainName.Length = cpu_to_le16(ln); } if (user == NULL) { SecurityBlob->UserName.Buffer = 0; SecurityBlob->UserName.Length = 0; SecurityBlob->UserName.MaximumLength = 0; } else { - __u16 len = - cifs_strtoUCS((__le16 *) bcc_ptr, user, 64, + __u16 ln = cifs_strtoUCS((__le16 *) bcc_ptr, user, 64, nls_codepage); - len *= 2; + ln *= 2; SecurityBlob->UserName.MaximumLength = - cpu_to_le16(len); + cpu_to_le16(ln); SecurityBlob->UserName.Buffer = cpu_to_le32(SecurityBlobLength); - bcc_ptr += len; - SecurityBlobLength += len; - SecurityBlob->UserName.Length = - cpu_to_le16(len); + bcc_ptr += ln; + SecurityBlobLength += ln; + SecurityBlob->UserName.Length = cpu_to_le16(ln); } /* SecurityBlob->WorkstationName.Length = @@ -3052,33 +3060,32 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, SecurityBlob->DomainName.Length = 0; SecurityBlob->DomainName.MaximumLength = 0; } else { - __u16 len; + __u16 ln; negotiate_flags |= NTLMSSP_NEGOTIATE_DOMAIN_SUPPLIED; strncpy(bcc_ptr, domain, 63); - len = strnlen(domain, 64); + ln = strnlen(domain, 64); SecurityBlob->DomainName.MaximumLength = - cpu_to_le16(len); + cpu_to_le16(ln); SecurityBlob->DomainName.Buffer = cpu_to_le32(SecurityBlobLength); - bcc_ptr += len; - SecurityBlobLength += len; - SecurityBlob->DomainName.Length = cpu_to_le16(len); + bcc_ptr += ln; + SecurityBlobLength += ln; + SecurityBlob->DomainName.Length = cpu_to_le16(ln); } if (user == NULL) { SecurityBlob->UserName.Buffer = 0; SecurityBlob->UserName.Length = 0; SecurityBlob->UserName.MaximumLength = 0; } else { - __u16 len; + __u16 ln; strncpy(bcc_ptr, user, 63); - len = strnlen(user, 64); - SecurityBlob->UserName.MaximumLength = - cpu_to_le16(len); + ln = strnlen(user, 64); + SecurityBlob->UserName.MaximumLength = cpu_to_le16(ln); SecurityBlob->UserName.Buffer = - cpu_to_le32(SecurityBlobLength); - bcc_ptr += len; - SecurityBlobLength += len; - SecurityBlob->UserName.Length = cpu_to_le16(len); + cpu_to_le32(SecurityBlobLength); + bcc_ptr += ln; + SecurityBlobLength += ln; + SecurityBlob->UserName.Length = cpu_to_le16(ln); } /* BB fill in our workstation name if known BB */ @@ -3100,12 +3107,11 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, rc = SendReceive(xid, ses, smb_buffer, smb_buffer_response, &bytes_returned, 1); if (rc) { -/* rc = map_smb_to_linux_error(smb_buffer_response); *//* done in SendReceive now */ - } else if ((smb_buffer_response->WordCount == 3) - || (smb_buffer_response->WordCount == 4)) { +/* rc = map_smb_to_linux_error(smb_buffer_response) done in SendReceive now */ + } else if ((smb_buffer_response->WordCount == 3) || + (smb_buffer_response->WordCount == 4)) { __u16 action = le16_to_cpu(pSMBr->resp.Action); - __u16 blob_len = - le16_to_cpu(pSMBr->resp.SecurityBlobLength); + __u16 blob_len = le16_to_cpu(pSMBr->resp.SecurityBlobLength); if (action & GUEST_LOGIN) cFYI(1, (" Guest login")); /* BB Should we set anything in SesInfo struct ? */ @@ -3145,8 +3151,8 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, } else { remaining_words = BCC(smb_buffer_response) / 2; } - len = - UniStrnlen((wchar_t *) bcc_ptr,remaining_words - 1); + len = UniStrnlen((wchar_t *) bcc_ptr, + remaining_words - 1); /* We look for obvious messed up bcc or strings in response so we do not go off the end since (at least) WIN2K and Windows XP have a major bug in not null terminating last Unicode string in response */ @@ -3230,7 +3236,7 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, <= BCC(smb_buffer_response)) { if (ses->serverOS) kfree(ses->serverOS); - ses->serverOS = kzalloc(len + 1,GFP_KERNEL); + ses->serverOS = kzalloc(len + 1, GFP_KERNEL); strncpy(ses->serverOS,bcc_ptr, len); bcc_ptr += len; @@ -3259,28 +3265,24 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, bcc_ptr[0] = 0; bcc_ptr++; } else - cFYI(1, - ("field of length %d " + cFYI(1, ("field of length %d " "extends beyond end of smb ", len)); } } else { - cERROR(1, - (" Security Blob extends beyond end " + cERROR(1, ("Security Blob extends beyond end " "of SMB")); } } else { cERROR(1, ("No session structure passed in.")); } } else { - cERROR(1, - (" Invalid Word count %d: ", + cERROR(1, ("Invalid Word count %d: ", smb_buffer_response->WordCount)); rc = -EIO; } - if (smb_buffer) - cifs_buf_release(smb_buffer); + cifs_buf_release(smb_buffer); return rc; } @@ -3389,6 +3391,18 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses, bcc_ptr = pByteArea(smb_buffer_response); length = strnlen(bcc_ptr, BCC(smb_buffer_response) - 2); /* skip service field (NB: this field is always ASCII) */ + if (length == 3) { + if ((bcc_ptr[0] == 'I') && (bcc_ptr[1] == 'P') && + (bcc_ptr[2] == 'C')) { + cFYI(1, ("IPC connection")); + tcon->ipc = 1; + } + } else if (length == 2) { + if ((bcc_ptr[0] == 'A') && (bcc_ptr[1] == ':')) { + /* the most common case */ + cFYI(1, ("disk share connection")); + } + } bcc_ptr += length + 1; strncpy(tcon->treeName, tree, MAX_TREE_SIZE); if (smb_buffer->Flags2 & SMBFLG2_UNICODE) { @@ -3399,9 +3413,11 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses, kfree(tcon->nativeFileSystem); tcon->nativeFileSystem = kzalloc(length + 2, GFP_KERNEL); - cifs_strfromUCS_le(tcon->nativeFileSystem, - (__le16 *) bcc_ptr, - length, nls_codepage); + if (tcon->nativeFileSystem) + cifs_strfromUCS_le( + tcon->nativeFileSystem, + (__le16 *) bcc_ptr, + length, nls_codepage); bcc_ptr += 2 * length; bcc_ptr[0] = 0; /* null terminate the string */ bcc_ptr[1] = 0; @@ -3416,8 +3432,9 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses, kfree(tcon->nativeFileSystem); tcon->nativeFileSystem = kzalloc(length + 1, GFP_KERNEL); - strncpy(tcon->nativeFileSystem, bcc_ptr, - length); + if (tcon->nativeFileSystem) + strncpy(tcon->nativeFileSystem, bcc_ptr, + length); } /* else do not bother copying these information fields*/ } @@ -3433,8 +3450,7 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses, ses->ipc_tid = smb_buffer_response->Tid; } - if (smb_buffer) - cifs_buf_release(smb_buffer); + cifs_buf_release(smb_buffer); return rc; } diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 4830acc..793404b 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -3,7 +3,7 @@ * * vfs operations that deal with dentries * - * Copyright (C) International Business Machines Corp., 2002,2005 + * Copyright (C) International Business Machines Corp., 2002,2007 * Author(s): Steve French (sfrench@us.ibm.com) * * This library is free software; you can redistribute it and/or modify @@ -269,7 +269,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, CIFSSMBClose(xid, pTcon, fileHandle); } else if (newinode) { pCifsFile = - kzalloc(sizeof (struct cifsFileInfo), GFP_KERNEL); + kzalloc(sizeof(struct cifsFileInfo), GFP_KERNEL); if (pCifsFile == NULL) goto cifs_create_out; @@ -397,7 +397,7 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode, /* BB Do not bother to decode buf since no local inode yet to put timestamps in, but we can reuse it safely */ - int bytes_written; + unsigned int bytes_written; struct win_dev *pdev; pdev = (struct win_dev *)buf; if (S_ISCHR(mode)) { @@ -450,8 +450,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, xid = GetXid(); - cFYI(1, - (" parent inode = 0x%p name is: %s and dentry = 0x%p", + cFYI(1, (" parent inode = 0x%p name is: %s and dentry = 0x%p", parent_dir_inode, direntry->d_name.name, direntry)); /* check whether path exists */ diff --git a/fs/cifs/export.c b/fs/cifs/export.c index 893fd0a..d614b91 100644 --- a/fs/cifs/export.c +++ b/fs/cifs/export.c @@ -43,6 +43,7 @@ #include <linux/exportfs.h> #include "cifsglob.h" #include "cifs_debug.h" +#include "cifsfs.h" #ifdef CONFIG_CIFS_EXPERIMENTAL static struct dentry *cifs_get_parent(struct dentry *dentry) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 894b1f7..1e7e4c0 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -467,7 +467,7 @@ reopen_error_exit: int cifs_close(struct inode *inode, struct file *file) { int rc = 0; - int xid; + int xid, timeout; struct cifs_sb_info *cifs_sb; struct cifsTconInfo *pTcon; struct cifsFileInfo *pSMBFile = @@ -485,9 +485,9 @@ int cifs_close(struct inode *inode, struct file *file) /* no sense reconnecting to close a file that is already closed */ if (pTcon->tidStatus != CifsNeedReconnect) { - int timeout = 2; + timeout = 2; while ((atomic_read(&pSMBFile->wrtPending) != 0) - && (timeout < 1000) ) { + && (timeout <= 2048)) { /* Give write a better chance to get to server ahead of the close. We do not want to add a wait_q here as it would @@ -522,12 +522,30 @@ int cifs_close(struct inode *inode, struct file *file) list_del(&pSMBFile->flist); list_del(&pSMBFile->tlist); write_unlock(&GlobalSMBSeslock); + timeout = 10; + /* We waited above to give the SMBWrite a chance to issue + on the wire (so we do not get SMBWrite returning EBADF + if writepages is racing with close. Note that writepages + does not specify a file handle, so it is possible for a file + to be opened twice, and the application close the "wrong" + file handle - in these cases we delay long enough to allow + the SMBWrite to get on the wire before the SMB Close. + We allow total wait here over 45 seconds, more than + oplock break time, and more than enough to allow any write + to complete on the server, or to time out on the client */ + while ((atomic_read(&pSMBFile->wrtPending) != 0) + && (timeout <= 50000)) { + cERROR(1, ("writes pending, delay free of handle")); + msleep(timeout); + timeout *= 8; + } kfree(pSMBFile->search_resume_name); kfree(file->private_data); file->private_data = NULL; } else rc = -EBADF; + read_lock(&GlobalSMBSeslock); if (list_empty(&(CIFS_I(inode)->openFileList))) { cFYI(1, ("closing last open instance for inode %p", inode)); /* if the file is not open we do not know if we can cache info @@ -535,6 +553,7 @@ int cifs_close(struct inode *inode, struct file *file) CIFS_I(inode)->clientCanCacheRead = FALSE; CIFS_I(inode)->clientCanCacheAll = FALSE; } + read_unlock(&GlobalSMBSeslock); if ((rc == 0) && CIFS_I(inode)->write_behind_rc) rc = CIFS_I(inode)->write_behind_rc; FreeXid(xid); @@ -767,7 +786,8 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *pfLock) mutex_lock(&fid->lock_mutex); list_for_each_entry_safe(li, tmp, &fid->llist, llist) { if (pfLock->fl_start <= li->offset && - length >= li->length) { + (pfLock->fl_start + length) >= + (li->offset + li->length)) { stored_rc = CIFSSMBLock(xid, pTcon, netfid, li->length, li->offset, @@ -1022,6 +1042,7 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode) } read_lock(&GlobalSMBSeslock); +refind_writable: list_for_each_entry(open_file, &cifs_inode->openFileList, flist) { if (open_file->closePend) continue; @@ -1029,24 +1050,49 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode) ((open_file->pfile->f_flags & O_RDWR) || (open_file->pfile->f_flags & O_WRONLY))) { atomic_inc(&open_file->wrtPending); + + if (!open_file->invalidHandle) { + /* found a good writable file */ + read_unlock(&GlobalSMBSeslock); + return open_file; + } + read_unlock(&GlobalSMBSeslock); - if ((open_file->invalidHandle) && - (!open_file->closePend) /* BB fixme -since the second clause can not be true remove it BB */) { - rc = cifs_reopen_file(open_file->pfile, FALSE); - /* if it fails, try another handle - might be */ - /* dangerous to hold up writepages with retry */ - if (rc) { - cFYI(1, - ("failed on reopen file in wp")); + /* Had to unlock since following call can block */ + rc = cifs_reopen_file(open_file->pfile, FALSE); + if (!rc) { + if (!open_file->closePend) + return open_file; + else { /* start over in case this was deleted */ + /* since the list could be modified */ read_lock(&GlobalSMBSeslock); - /* can not use this handle, no write - pending on this one after all */ - atomic_dec - (&open_file->wrtPending); - continue; + atomic_dec(&open_file->wrtPending); + goto refind_writable; } } - return open_file; + + /* if it fails, try another handle if possible - + (we can not do this if closePending since + loop could be modified - in which case we + have to start at the beginning of the list + again. Note that it would be bad + to hold up writepages here (rather than + in caller) with continuous retries */ + cFYI(1, ("wp failed on reopen file")); + read_lock(&GlobalSMBSeslock); + /* can not use this handle, no write + pending on this one after all */ + atomic_dec(&open_file->wrtPending); + + if (open_file->closePend) /* list could have changed */ + goto refind_writable; + /* else we simply continue to the next entry. Thus + we do not loop on reopen errors. If we + can not reopen the file, for example if we + reconnected to a server with another client + racing to delete or lock the file we would not + make progress if we restarted before the beginning + of the loop here. */ } } read_unlock(&GlobalSMBSeslock); @@ -1709,7 +1755,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, struct page *page; struct cifs_sb_info *cifs_sb; struct cifsTconInfo *pTcon; - int bytes_read = 0; + unsigned int bytes_read = 0; unsigned int read_size, i; char *smb_read_data = NULL; struct smb_com_read_rsp *pSMBr; @@ -1803,7 +1849,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, i += bytes_read >> PAGE_CACHE_SHIFT; cifs_stats_bytes_read(pTcon, bytes_read); - if ((int)(bytes_read & PAGE_CACHE_MASK) != bytes_read) { + if ((bytes_read & PAGE_CACHE_MASK) != bytes_read) { i++; /* account for partial page */ /* server copy of file can have smaller size diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index dd41677..5e8b388 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -115,7 +115,7 @@ int cifs_get_inode_info_unix(struct inode **pinode, inode->i_mode = le64_to_cpu(findData.Permissions); /* since we set the inode type below we need to mask off to avoid strange results if bits set above */ - inode->i_mode &= ~S_IFMT; + inode->i_mode &= ~S_IFMT; if (type == UNIX_FILE) { inode->i_mode |= S_IFREG; } else if (type == UNIX_SYMLINK) { @@ -575,19 +575,33 @@ int cifs_get_inode_info(struct inode **pinode, return rc; } +static const struct inode_operations cifs_ipc_inode_ops = { + .lookup = cifs_lookup, +}; + /* gets root inode */ void cifs_read_inode(struct inode *inode) { - int xid; + int xid, rc; struct cifs_sb_info *cifs_sb; cifs_sb = CIFS_SB(inode->i_sb); xid = GetXid(); if (cifs_sb->tcon->unix_ext) - cifs_get_inode_info_unix(&inode, "", inode->i_sb, xid); + rc = cifs_get_inode_info_unix(&inode, "", inode->i_sb, xid); else - cifs_get_inode_info(&inode, "", NULL, inode->i_sb, xid); + rc = cifs_get_inode_info(&inode, "", NULL, inode->i_sb, xid); + if (rc && cifs_sb->tcon->ipc) { + cFYI(1, ("ipc connection - fake read inode")); + inode->i_mode |= S_IFDIR; + inode->i_nlink = 2; + inode->i_op = &cifs_ipc_inode_ops; + inode->i_fop = &simple_dir_operations; + inode->i_uid = cifs_sb->mnt_uid; + inode->i_gid = cifs_sb->mnt_gid; + } + /* can not call macro FreeXid here since in a void func */ _FreeXid(xid); } @@ -919,18 +933,25 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode) goto mkdir_out; } + mode &= ~current->fs->umask; rc = CIFSPOSIXCreate(xid, pTcon, SMB_O_DIRECTORY | SMB_O_CREAT, mode, NULL /* netfid */, pInfo, &oplock, full_path, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); - if (rc) { + if (rc == -EOPNOTSUPP) { + kfree(pInfo); + goto mkdir_retry_old; + } else if (rc) { cFYI(1, ("posix mkdir returned 0x%x", rc)); d_drop(direntry); } else { int obj_type; - if (pInfo->Type == -1) /* no return info - go query */ + if (pInfo->Type == cpu_to_le32(-1)) { + /* no return info, go query for it */ + kfree(pInfo); goto mkdir_get_info; + } /*BB check (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID ) to see if need to set uid/gid */ inc_nlink(inode); @@ -940,8 +961,10 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode) direntry->d_op = &cifs_dentry_ops; newinode = new_inode(inode->i_sb); - if (newinode == NULL) + if (newinode == NULL) { + kfree(pInfo); goto mkdir_get_info; + } /* Is an i_ino of zero legal? */ /* Are there sanity checks we can use to ensure that the server is really filling in that field? */ @@ -972,7 +995,7 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode) kfree(pInfo); goto mkdir_out; } - +mkdir_retry_old: /* BB add setting the equivalent of mode via CreateX w/ACLs */ rc = CIFSSMBMkDir(xid, pTcon, full_path, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); @@ -1377,8 +1400,17 @@ static int cifs_vmtruncate(struct inode *inode, loff_t offset) } i_size_write(inode, offset); spin_unlock(&inode->i_lock); + /* + * unmap_mapping_range is called twice, first simply for efficiency + * so that truncate_inode_pages does fewer single-page unmaps. However + * after this first call, and before truncate_inode_pages finishes, + * it is possible for private pages to be COWed, which remain after + * truncate_inode_pages finishes, hence the second unmap_mapping_range + * call must be made for correctness. + */ unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1); truncate_inode_pages(mapping, offset); + unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1); goto out_truncate; do_expand: @@ -1469,7 +1501,7 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs) atomic_dec(&open_file->wrtPending); cFYI(1, ("SetFSize for attrs rc = %d", rc)); if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) { - int bytes_written; + unsigned int bytes_written; rc = CIFSSMBWrite(xid, pTcon, nfid, 0, attrs->ia_size, &bytes_written, NULL, NULL, @@ -1502,7 +1534,7 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs) cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); if (rc == 0) { - int bytes_written; + unsigned int bytes_written; rc = CIFSSMBWrite(xid, pTcon, netfid, 0, attrs->ia_size, @@ -1538,6 +1570,11 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs) } time_buf.Attributes = 0; + + /* skip mode change if it's just for clearing setuid/setgid */ + if (attrs->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) + attrs->ia_valid &= ~ATTR_MODE; + if (attrs->ia_valid & ATTR_MODE) { cFYI(1, ("Mode changed to 0x%x", attrs->ia_mode)); mode = attrs->ia_mode; diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 6a85ef7..11f2657 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -237,7 +237,7 @@ cifs_readlink(struct dentry *direntry, char __user *pBuffer, int buflen) char *tmp_path = NULL; char *tmpbuffer; unsigned char *referrals = NULL; - int num_referrals = 0; + unsigned int num_referrals = 0; int len; __u16 fid; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 0bcec08..51ec681 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -169,7 +169,6 @@ cifs_buf_get(void) void cifs_buf_release(void *buf_to_free) { - if (buf_to_free == NULL) { /* cFYI(1, ("Null buffer passed to cifs_buf_release"));*/ return; diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index 2bfed3f..f06359c 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -114,10 +114,16 @@ static const struct smb_to_posix_error mapping_table_ERRSRV[] = { {ERRusempx, -EIO}, {ERRusestd, -EIO}, {ERR_NOTIFY_ENUM_DIR, -ENOBUFS}, - {ERRaccountexpired, -EACCES}, + {ERRnoSuchUser, -EACCES}, +/* {ERRaccountexpired, -EACCES}, {ERRbadclient, -EACCES}, {ERRbadLogonTime, -EACCES}, - {ERRpasswordExpired, -EACCES}, + {ERRpasswordExpired, -EACCES},*/ + {ERRaccountexpired, -EKEYEXPIRED}, + {ERRbadclient, -EACCES}, + {ERRbadLogonTime, -EACCES}, + {ERRpasswordExpired, -EKEYEXPIRED}, + {ERRnosupport, -EINVAL}, {0, 0} }; @@ -270,7 +276,7 @@ static const struct { from NT_STATUS_NO_SUCH_USER to NT_STATUS_LOGON_FAILURE during the session setup } */ { - ERRDOS, ERRnoaccess, NT_STATUS_NO_SUCH_USER}, { + ERRDOS, ERRnoaccess, NT_STATUS_NO_SUCH_USER}, { /* could map to 2238 */ ERRHRD, ERRgeneral, NT_STATUS_GROUP_EXISTS}, { ERRHRD, ERRgeneral, NT_STATUS_NO_SUCH_GROUP}, { ERRHRD, ERRgeneral, NT_STATUS_MEMBER_IN_GROUP}, { @@ -285,10 +291,10 @@ static const struct { ERRHRD, ERRgeneral, NT_STATUS_PASSWORD_RESTRICTION}, { ERRDOS, ERRnoaccess, NT_STATUS_LOGON_FAILURE}, { ERRHRD, ERRgeneral, NT_STATUS_ACCOUNT_RESTRICTION}, { - ERRSRV, 2241, NT_STATUS_INVALID_LOGON_HOURS}, { - ERRSRV, 2240, NT_STATUS_INVALID_WORKSTATION}, { + ERRSRV, ERRbadLogonTime, NT_STATUS_INVALID_LOGON_HOURS}, { + ERRSRV, ERRbadclient, NT_STATUS_INVALID_WORKSTATION}, { ERRSRV, ERRpasswordExpired, NT_STATUS_PASSWORD_EXPIRED}, { - ERRSRV, 2239, NT_STATUS_ACCOUNT_DISABLED}, { + ERRSRV, ERRaccountexpired, NT_STATUS_ACCOUNT_DISABLED}, { ERRHRD, ERRgeneral, NT_STATUS_NONE_MAPPED}, { ERRHRD, ERRgeneral, NT_STATUS_TOO_MANY_LUIDS_REQUESTED}, { ERRHRD, ERRgeneral, NT_STATUS_LUIDS_EXHAUSTED}, { @@ -585,7 +591,7 @@ static const struct { ERRDOS, ERRnoaccess, NT_STATUS_TRUST_FAILURE}, { ERRHRD, ERRgeneral, NT_STATUS_MUTANT_LIMIT_EXCEEDED}, { ERRDOS, ERRnetlogonNotStarted, NT_STATUS_NETLOGON_NOT_STARTED}, { - ERRSRV, 2239, NT_STATUS_ACCOUNT_EXPIRED}, { + ERRSRV, ERRaccountexpired, NT_STATUS_ACCOUNT_EXPIRED}, { ERRHRD, ERRgeneral, NT_STATUS_POSSIBLE_DEADLOCK}, { ERRHRD, ERRgeneral, NT_STATUS_NETWORK_CREDENTIAL_CONFLICT}, { ERRHRD, ERRgeneral, NT_STATUS_REMOTE_SESSION_LIMIT}, { @@ -754,7 +760,7 @@ ntstatus_to_dos(__u32 ntstatus, __u8 * eclass, __u16 * ecode) } int -map_smb_to_linux_error(struct smb_hdr *smb) +map_smb_to_linux_error(struct smb_hdr *smb, int logErr) { unsigned int i; int rc = -EIO; /* if transport error smb error may not be set */ @@ -771,7 +777,9 @@ map_smb_to_linux_error(struct smb_hdr *smb) /* translate the newer STATUS codes to old style SMB errors * and then to POSIX errors */ __u32 err = le32_to_cpu(smb->Status.CifsError); - if (cifsFYI & CIFS_RC) + if (logErr && (err != (NT_STATUS_MORE_PROCESSING_REQUIRED))) + cifs_print_status(err); + else if (cifsFYI & CIFS_RC) cifs_print_status(err); ntstatus_to_dos(err, &smberrclass, &smberrcode); } else { @@ -813,7 +821,7 @@ map_smb_to_linux_error(struct smb_hdr *smb) } /* else ERRHRD class errors or junk - return EIO */ - cFYI(1, (" !!Mapping smb error code %d to POSIX err %d !!", + cFYI(1, ("Mapping smb error code %d to POSIX err %d", smberrcode, rc)); /* generic corrective action e.g. reconnect SMB session on @@ -899,8 +907,11 @@ struct timespec cnvrtDosUnixTm(__u16 date, __u16 time) cERROR(1, ("illegal hours %d", st->Hours)); days = sd->Day; month = sd->Month; - if ((days > 31) || (month > 12)) + if ((days > 31) || (month > 12)) { cERROR(1, ("illegal date, month %d day: %d", month, days)); + if (month > 12) + month = 12; + } month -= 1; days += total_days_of_prev_months[month]; days += 3652; /* account for difference in days between 1980 and 1970 */ diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 916df94..3746580 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -121,7 +121,7 @@ static void AdjustForTZ(struct cifsTconInfo *tcon, struct inode *inode) static void fill_in_inode(struct inode *tmp_inode, int new_buf_type, - char *buf, int *pobject_type, int isNewInode) + char *buf, unsigned int *pobject_type, int isNewInode) { loff_t local_size; struct timespec local_mtime; @@ -294,7 +294,7 @@ static void fill_in_inode(struct inode *tmp_inode, int new_buf_type, } static void unix_fill_in_inode(struct inode *tmp_inode, - FILE_UNIX_INFO *pfindData, int *pobject_type, int isNewInode) + FILE_UNIX_INFO *pfindData, unsigned int *pobject_type, int isNewInode) { loff_t local_size; struct timespec local_mtime; @@ -826,7 +826,7 @@ static int cifs_filldir(char *pfindEntry, struct file *file, int rc = 0; struct qstr qstring; struct cifsFileInfo *pCifsF; - unsigned obj_type; + unsigned int obj_type; ino_t inum; struct cifs_sb_info *cifs_sb; struct inode *tmp_inode; @@ -1067,7 +1067,7 @@ int cifs_readdir(struct file *file, void *direntry, filldir_t filldir) for (i = 0; (i < num_to_fill) && (rc == 0); i++) { if (current_entry == NULL) { /* evaluate whether this case is an error */ - cERROR(1,("past end of SMB num to fill %d i %d", + cERROR(1, ("past SMB end, num to fill %d i %d", num_to_fill, i)); break; } diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 892be9b..899dc60 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -67,14 +67,59 @@ static __u32 cifs_ssetup_hdr(struct cifsSesInfo *ses, SESSION_SETUP_ANDX *pSMB) pSMB->req.hdr.Flags2 |= SMBFLG2_DFS; capabilities |= CAP_DFS; } - if (ses->capabilities & CAP_UNIX) { + if (ses->capabilities & CAP_UNIX) capabilities |= CAP_UNIX; - } /* BB check whether to init vcnum BB */ return capabilities; } +static void +unicode_oslm_strings(char **pbcc_area, const struct nls_table *nls_cp) +{ + char *bcc_ptr = *pbcc_area; + int bytes_ret = 0; + + /* Copy OS version */ + bytes_ret = cifs_strtoUCS((__le16 *)bcc_ptr, "Linux version ", 32, + nls_cp); + bcc_ptr += 2 * bytes_ret; + bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, init_utsname()->release, + 32, nls_cp); + bcc_ptr += 2 * bytes_ret; + bcc_ptr += 2; /* trailing null */ + + bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, CIFS_NETWORK_OPSYS, + 32, nls_cp); + bcc_ptr += 2 * bytes_ret; + bcc_ptr += 2; /* trailing null */ + + *pbcc_area = bcc_ptr; +} + +static void unicode_domain_string(char **pbcc_area, struct cifsSesInfo *ses, + const struct nls_table *nls_cp) +{ + char *bcc_ptr = *pbcc_area; + int bytes_ret = 0; + + /* copy domain */ + if (ses->domainName == NULL) { + /* Sending null domain better than using a bogus domain name (as + we did briefly in 2.6.18) since server will use its default */ + *bcc_ptr = 0; + *(bcc_ptr+1) = 0; + bytes_ret = 0; + } else + bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, ses->domainName, + 256, nls_cp); + bcc_ptr += 2 * bytes_ret; + bcc_ptr += 2; /* account for null terminator */ + + *pbcc_area = bcc_ptr; +} + + static void unicode_ssetup_strings(char **pbcc_area, struct cifsSesInfo *ses, const struct nls_table *nls_cp) { @@ -100,32 +145,9 @@ static void unicode_ssetup_strings(char **pbcc_area, struct cifsSesInfo *ses, } bcc_ptr += 2 * bytes_ret; bcc_ptr += 2; /* account for null termination */ - /* copy domain */ - if (ses->domainName == NULL) { - /* Sending null domain better than using a bogus domain name (as - we did briefly in 2.6.18) since server will use its default */ - *bcc_ptr = 0; - *(bcc_ptr+1) = 0; - bytes_ret = 0; - } else - bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, ses->domainName, - 256, nls_cp); - bcc_ptr += 2 * bytes_ret; - bcc_ptr += 2; /* account for null terminator */ - - /* Copy OS version */ - bytes_ret = cifs_strtoUCS((__le16 *)bcc_ptr, "Linux version ", 32, - nls_cp); - bcc_ptr += 2 * bytes_ret; - bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, init_utsname()->release, - 32, nls_cp); - bcc_ptr += 2 * bytes_ret; - bcc_ptr += 2; /* trailing null */ - bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, CIFS_NETWORK_OPSYS, - 32, nls_cp); - bcc_ptr += 2 * bytes_ret; - bcc_ptr += 2; /* trailing null */ + unicode_domain_string(&bcc_ptr, ses, nls_cp); + unicode_oslm_strings(&bcc_ptr, nls_cp); *pbcc_area = bcc_ptr; } @@ -203,14 +225,11 @@ static int decode_unicode_ssetup(char **pbcc_area, int bleft, if (len >= words_left) return rc; - if (ses->serverOS) - kfree(ses->serverOS); + kfree(ses->serverOS); /* UTF-8 string will not grow more than four times as big as UCS-16 */ ses->serverOS = kzalloc(4 * len, GFP_KERNEL); - if (ses->serverOS != NULL) { - cifs_strfromUCS_le(ses->serverOS, (__le16 *)data, len, - nls_cp); - } + if (ses->serverOS != NULL) + cifs_strfromUCS_le(ses->serverOS, (__le16 *)data, len, nls_cp); data += 2 * (len + 1); words_left -= len + 1; @@ -220,8 +239,7 @@ static int decode_unicode_ssetup(char **pbcc_area, int bleft, if (len >= words_left) return rc; - if (ses->serverNOS) - kfree(ses->serverNOS); + kfree(ses->serverNOS); ses->serverNOS = kzalloc(4 * len, GFP_KERNEL); /* BB this is wrong length FIXME BB */ if (ses->serverNOS != NULL) { cifs_strfromUCS_le(ses->serverNOS, (__le16 *)data, len, @@ -240,8 +258,7 @@ static int decode_unicode_ssetup(char **pbcc_area, int bleft, if (len > words_left) return rc; - if (ses->serverDomain) - kfree(ses->serverDomain); + kfree(ses->serverDomain); ses->serverDomain = kzalloc(2 * (len + 1), GFP_KERNEL); /* BB FIXME wrong length */ if (ses->serverDomain != NULL) { cifs_strfromUCS_le(ses->serverDomain, (__le16 *)data, len, @@ -271,8 +288,7 @@ static int decode_ascii_ssetup(char **pbcc_area, int bleft, if (len >= bleft) return rc; - if (ses->serverOS) - kfree(ses->serverOS); + kfree(ses->serverOS); ses->serverOS = kzalloc(len + 1, GFP_KERNEL); if (ses->serverOS) @@ -289,8 +305,7 @@ static int decode_ascii_ssetup(char **pbcc_area, int bleft, if (len >= bleft) return rc; - if (ses->serverNOS) - kfree(ses->serverNOS); + kfree(ses->serverNOS); ses->serverNOS = kzalloc(len + 1, GFP_KERNEL); if (ses->serverNOS) @@ -479,7 +494,8 @@ CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses, int first_time, if (ses->capabilities & CAP_UNICODE) { if (iov[0].iov_len % 2) { *bcc_ptr = 0; - } bcc_ptr++; + bcc_ptr++; + } unicode_ssetup_strings(&bcc_ptr, ses, nls_cp); } else ascii_ssetup_strings(&bcc_ptr, ses, nls_cp); @@ -497,7 +513,8 @@ CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses, int first_time, iov[1].iov_base = str_area; iov[1].iov_len = count; - rc = SendReceive2(xid, ses, iov, 2 /* num_iovecs */, &resp_buf_type, 0); + rc = SendReceive2(xid, ses, iov, 2 /* num_iovecs */, &resp_buf_type, + 0 /* not long op */, 1 /* log NT STATUS if any */ ); /* SMB request buf freed in SendReceive2 */ cFYI(1, ("ssetup rc from sendrecv2 is %d", rc)); diff --git a/fs/cifs/smberr.h b/fs/cifs/smberr.h index 2ef0be2..7f50e85 100644 --- a/fs/cifs/smberr.h +++ b/fs/cifs/smberr.h @@ -173,9 +173,10 @@ #define ERRusestd 251 /* temporarily unable to use either raw or mpx */ #define ERR_NOTIFY_ENUM_DIR 1024 +#define ERRnoSuchUser 2238 /* user account does not exist */ #define ERRaccountexpired 2239 -#define ERRbadclient 2240 -#define ERRbadLogonTime 2241 +#define ERRbadclient 2240 /* can not logon from this client */ +#define ERRbadLogonTime 2241 /* logon hours do not allow this */ #define ERRpasswordExpired 2242 #define ERRnetlogonNotStarted 2455 #define ERRnosupport 0xFFFF diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 746bc94..7ed32b3 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -55,7 +55,7 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct cifsSesInfo *ses) if (temp == NULL) return temp; else { - memset(temp, 0, sizeof (struct mid_q_entry)); + memset(temp, 0, sizeof(struct mid_q_entry)); temp->mid = smb_buffer->Mid; /* always LE */ temp->pid = current->pid; temp->command = smb_buffer->Command; @@ -158,7 +158,7 @@ smb_send(struct socket *ssocket, struct smb_hdr *smb_buffer, iov.iov_len = len; smb_msg.msg_name = sin; - smb_msg.msg_namelen = sizeof (struct sockaddr); + smb_msg.msg_namelen = sizeof(struct sockaddr); smb_msg.msg_control = NULL; smb_msg.msg_controllen = 0; smb_msg.msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL; /* BB add more flags?*/ @@ -228,7 +228,7 @@ smb_send2(struct socket *ssocket, struct kvec *iov, int n_vec, return -ENOTSOCK; /* BB eventually add reconnect code here */ smb_msg.msg_name = sin; - smb_msg.msg_namelen = sizeof (struct sockaddr); + smb_msg.msg_namelen = sizeof(struct sockaddr); smb_msg.msg_control = NULL; smb_msg.msg_controllen = 0; smb_msg.msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL; /* BB add more flags?*/ @@ -363,9 +363,8 @@ static int allocate_mid(struct cifsSesInfo *ses, struct smb_hdr *in_buf, } /* else ok - we are setting up session */ } *ppmidQ = AllocMidQEntry(in_buf, ses); - if (*ppmidQ == NULL) { + if (*ppmidQ == NULL) return -ENOMEM; - } return 0; } @@ -419,7 +418,7 @@ static int wait_for_response(struct cifsSesInfo *ses, int SendReceive2(const unsigned int xid, struct cifsSesInfo *ses, struct kvec *iov, int n_vec, int *pRespBufType /* ret */, - const int long_op) + const int long_op, const int logError) { int rc = 0; unsigned int receive_len; @@ -465,7 +464,6 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses, wake_up(&ses->server->request_q); return rc; } - rc = cifs_sign_smb2(iov, n_vec, ses->server, &midQ->sequence_number); midQ->midState = MID_REQUEST_SUBMITTED; @@ -568,13 +566,11 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses, } /* BB special case reconnect tid and uid here? */ - /* BB special case Errbadpassword and pwdexpired here */ - rc = map_smb_to_linux_error(midQ->resp_buf); + rc = map_smb_to_linux_error(midQ->resp_buf, logError); /* convert ByteCount if necessary */ - if (receive_len >= - sizeof (struct smb_hdr) - - 4 /* do not count RFC1001 header */ + + if (receive_len >= sizeof(struct smb_hdr) - 4 + /* do not count RFC1001 header */ + (2 * midQ->resp_buf->WordCount) + 2 /* bcc */ ) BCC(midQ->resp_buf) = le16_to_cpu(BCC_LE(midQ->resp_buf)); @@ -749,12 +745,11 @@ SendReceive(const unsigned int xid, struct cifsSesInfo *ses, *pbytes_returned = out_buf->smb_buf_length; /* BB special case reconnect tid and uid here? */ - rc = map_smb_to_linux_error(out_buf); + rc = map_smb_to_linux_error(out_buf, 0 /* no log */ ); /* convert ByteCount if necessary */ - if (receive_len >= - sizeof (struct smb_hdr) - - 4 /* do not count RFC1001 header */ + + if (receive_len >= sizeof(struct smb_hdr) - 4 + /* do not count RFC1001 header */ + (2 * out_buf->WordCount) + 2 /* bcc */ ) BCC(out_buf) = le16_to_cpu(BCC_LE(out_buf)); } else { @@ -993,12 +988,11 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifsTconInfo *tcon, *pbytes_returned = out_buf->smb_buf_length; /* BB special case reconnect tid and uid here? */ - rc = map_smb_to_linux_error(out_buf); + rc = map_smb_to_linux_error(out_buf, 0 /* no log */ ); /* convert ByteCount if necessary */ - if (receive_len >= - sizeof (struct smb_hdr) - - 4 /* do not count RFC1001 header */ + + if (receive_len >= sizeof(struct smb_hdr) - 4 + /* do not count RFC1001 header */ + (2 * out_buf->WordCount) + 2 /* bcc */ ) BCC(out_buf) = le16_to_cpu(BCC_LE(out_buf)); } else { diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index f61e433..369e838 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -261,21 +261,26 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); -/* else if(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) { +#ifdef CONFIG_CIFS_EXPERIMENTAL + else if(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) { __u16 fid; int oplock = FALSE; - rc = CIFSSMBOpen(xid, pTcon, full_path, - FILE_OPEN, GENERIC_READ, 0, &fid, - &oplock, NULL, cifs_sb->local_nls, - cifs_sb->mnt_cifs_flags & - CIFS_MOUNT_MAP_SPECIAL_CHR); + if (experimEnabled) + rc = CIFSSMBOpen(xid, pTcon, full_path, + FILE_OPEN, GENERIC_READ, 0, &fid, + &oplock, NULL, cifs_sb->local_nls, + cifs_sb->mnt_cifs_flags & + CIFS_MOUNT_MAP_SPECIAL_CHR); + /* else rc is EOPNOTSUPP from above */ + if(rc == 0) { rc = CIFSSMBGetCIFSACL(xid, pTcon, fid, ea_value, buf_size, ACL_TYPE_ACCESS); CIFSSMBClose(xid, pTcon, fid); } - } */ /* BB enable after fixing up return data */ + } +#endif /* EXPERIMENTAL */ #else cFYI(1, ("query POSIX ACL not supported yet")); #endif /* CONFIG_CIFS_POSIX */ diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c index cdb4c07..359e531 100644 --- a/fs/coda/upcall.c +++ b/fs/coda/upcall.c @@ -51,7 +51,7 @@ static void *alloc_upcall(int opcode, int size) inp->ih.opcode = opcode; inp->ih.pid = current->pid; - inp->ih.pgid = process_group(current); + inp->ih.pgid = task_pgrp_nr(current); #ifdef CONFIG_CODA_FS_OLD_API memset(&inp->ih.cred, 0, sizeof(struct coda_cred)); inp->ih.cred.cr_fsuid = current->fsuid; diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 6dacd39..a4284cc 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -3001,7 +3001,7 @@ static int __init init_sys32_ioctl(void) int i; for (i = 0; i < ARRAY_SIZE(ioctl_start); i++) { - if (ioctl_start[i].next != 0) { + if (ioctl_start[i].next) { printk("ioctl translation %d bad\n",i); return -1; } diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 5c817bd..350680f 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -148,7 +148,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i { struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; struct page *pages[BLKS_PER_BUF]; - unsigned i, blocknr, buffer, unread; + unsigned i, blocknr, buffer; unsigned long devsize; char *data; @@ -175,7 +175,6 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i devsize = mapping->host->i_size >> PAGE_CACHE_SHIFT; /* Ok, read in BLKS_PER_BUF pages completely first. */ - unread = 0; for (i = 0; i < BLKS_PER_BUF; i++) { struct page *page = NULL; @@ -362,7 +361,7 @@ static int cramfs_readdir(struct file *filp, void *dirent, filldir_t filldir) if (offset & 3) return -EINVAL; - buf = kmalloc(256, GFP_KERNEL); + buf = kmalloc(CRAMFS_MAXPATHLEN, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -376,7 +375,7 @@ static int cramfs_readdir(struct file *filp, void *dirent, filldir_t filldir) int namelen, error; mutex_lock(&read_mutex); - de = cramfs_read(sb, OFFSET(inode) + offset, sizeof(*de)+256); + de = cramfs_read(sb, OFFSET(inode) + offset, sizeof(*de)+CRAMFS_MAXPATHLEN); name = (char *)(de+1); /* @@ -426,7 +425,7 @@ static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, s char *name; int namelen, retval; - de = cramfs_read(dir->i_sb, OFFSET(dir) + offset, sizeof(*de)+256); + de = cramfs_read(dir->i_sb, OFFSET(dir) + offset, sizeof(*de)+CRAMFS_MAXPATHLEN); name = (char *)(de+1); /* Try to take advantage of sorted directories */ diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 6438941..4f74154 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -456,7 +456,7 @@ static int check_version(struct dlm_write_request *req) printk(KERN_DEBUG "dlm: process %s (%d) version mismatch " "user (%d.%d.%d) kernel (%d.%d.%d)\n", current->comm, - current->pid, + task_pid_nr(current), req->version[0], req->version[1], req->version[2], diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 5701f81..0b1ab01 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -914,6 +914,14 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia) if (rc < 0) goto out; } + + /* + * mode change is for clearing setuid/setgid bits. Allow lower fs + * to interpret this in its own way. + */ + if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) + ia->ia_valid &= ~ATTR_MODE; + rc = notify_change(lower_dentry, ia); out: fsstack_copy_attr_all(inode, lower_inode, NULL); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 77b9953..34f68f3 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -325,15 +325,14 @@ static void ep_poll_safewake(struct poll_safewake *psw, wait_queue_head_t *wq) int wake_nests = 0; unsigned long flags; struct task_struct *this_task = current; - struct list_head *lsthead = &psw->wake_task_list, *lnk; + struct list_head *lsthead = &psw->wake_task_list; struct wake_task_node *tncur; struct wake_task_node tnode; spin_lock_irqsave(&psw->lock, flags); /* Try to see if the current task is already inside this wakeup call */ - list_for_each(lnk, lsthead) { - tncur = list_entry(lnk, struct wake_task_node, llink); + list_for_each_entry(tncur, lsthead, llink) { if (tncur->wq == wq || (tncur->task == this_task && ++wake_nests > EP_MAX_POLLWAKE_NESTS)) { @@ -463,7 +462,7 @@ static void ep_free(struct eventpoll *ep) * holding "epmutex" we can be sure that no file cleanup code will hit * us during this operation. So we can avoid the lock on "ep->lock". */ - while ((rbp = rb_first(&ep->rbr)) != 0) { + while ((rbp = rb_first(&ep->rbr)) != NULL) { epi = rb_entry(rbp, struct epitem, rbn); ep_remove(ep, epi); } @@ -234,7 +234,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm) vma->vm_start = vma->vm_end - PAGE_SIZE; vma->vm_flags = VM_STACK_FLAGS; - vma->vm_page_prot = protection_map[vma->vm_flags & 0x7]; + vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); err = insert_vm_struct(mm, vma); if (err) { up_write(&mm->mmap_sem); @@ -775,8 +775,8 @@ 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(tsk->group_leader == child_reaper(tsk))) - tsk->nsproxy->pid_ns->child_reaper = tsk; + if (unlikely(tsk->group_leader == task_child_reaper(tsk))) + task_active_pid_ns(tsk)->child_reaper = tsk; zap_other_threads(tsk); read_unlock(&tasklist_lock); @@ -841,8 +841,8 @@ static int de_thread(struct task_struct *tsk) */ tsk->start_time = leader->start_time; - BUG_ON(leader->tgid != tsk->tgid); - BUG_ON(tsk->pid == tsk->tgid); + BUG_ON(!same_thread_group(leader, tsk)); + BUG_ON(has_group_leader_pid(tsk)); /* * An exec() starts a new thread group with the * TGID of the previous thread group. Rehash the @@ -857,7 +857,7 @@ static int de_thread(struct task_struct *tsk) */ detach_pid(tsk, PIDTYPE_PID); tsk->pid = leader->pid; - attach_pid(tsk, PIDTYPE_PID, find_pid(tsk->pid)); + attach_pid(tsk, PIDTYPE_PID, task_pid(leader)); transfer_pid(leader, tsk, PIDTYPE_PGID); transfer_pid(leader, tsk, PIDTYPE_SID); list_replace_rcu(&leader->tasks, &tsk->tasks); @@ -1433,7 +1433,7 @@ static int format_corename(char *corename, const char *pattern, long signr) case 'p': pid_in_pattern = 1; rc = snprintf(out_ptr, out_end - out_ptr, - "%d", current->tgid); + "%d", task_tgid_vnr(current)); if (rc > out_end - out_ptr) goto out; out_ptr += rc; @@ -1513,7 +1513,7 @@ static int format_corename(char *corename, const char *pattern, long signr) if (!ispipe && !pid_in_pattern && (core_uses_pid || atomic_read(¤t->mm->mm_users) != 1)) { rc = snprintf(out_ptr, out_end - out_ptr, - ".%d", current->tgid); + ".%d", task_tgid_vnr(current)); if (rc > out_end - out_ptr) goto out; out_ptr += rc; diff --git a/fs/ext3/fsync.c b/fs/ext3/fsync.c index dd1fd3c..a588e23 100644 --- a/fs/ext3/fsync.c +++ b/fs/ext3/fsync.c @@ -47,7 +47,7 @@ int ext3_sync_file(struct file * file, struct dentry *dentry, int datasync) struct inode *inode = dentry->d_inode; int ret = 0; - J_ASSERT(ext3_journal_current_handle() == 0); + J_ASSERT(ext3_journal_current_handle() == NULL); /* * data=writeback: diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 2f2b686..9b162cd 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1028,7 +1028,7 @@ struct buffer_head *ext3_getblk(handle_t *handle, struct inode *inode, } if (buffer_new(&dummy)) { J_ASSERT(create != 0); - J_ASSERT(handle != 0); + J_ASSERT(handle != NULL); /* * Now that we do not always journal data, we should @@ -2954,7 +2954,7 @@ int ext3_write_inode(struct inode *inode, int wait) return 0; if (ext3_journal_current_handle()) { - jbd_debug(0, "called recursively, non-PF_MEMALLOC!\n"); + jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n"); dump_stack(); return -EIO; } diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c index 771f7ad..44de145 100644 --- a/fs/ext3/resize.c +++ b/fs/ext3/resize.c @@ -245,10 +245,10 @@ static int setup_new_group_blocks(struct super_block *sb, brelse(gdb); goto exit_bh; } - lock_buffer(bh); - memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, bh->b_size); + lock_buffer(gdb); + memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, gdb->b_size); set_buffer_uptodate(gdb); - unlock_buffer(bh); + unlock_buffer(gdb); ext3_journal_dirty_metadata(handle, gdb); ext3_set_bit(bit, bh->b_data); brelse(gdb); diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 141573d..81868c0 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -1620,7 +1620,11 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) } brelse (bh); - sb_set_blocksize(sb, blocksize); + if (!sb_set_blocksize(sb, blocksize)) { + printk(KERN_ERR "EXT3-fs: bad blocksize %d.\n", + blocksize); + goto out_fail; + } logic_sb_block = (sb_block * EXT3_MIN_BLOCK_SIZE) / blocksize; offset = (sb_block * EXT3_MIN_BLOCK_SIZE) % blocksize; bh = sb_bread(sb, logic_sb_block); diff --git a/fs/ext3/xattr.c b/fs/ext3/xattr.c index f58cbb2..4083738 100644 --- a/fs/ext3/xattr.c +++ b/fs/ext3/xattr.c @@ -741,12 +741,11 @@ ext3_xattr_block_set(handle_t *handle, struct inode *inode, } } else { /* Allocate a buffer where we construct the new block. */ - s->base = kmalloc(sb->s_blocksize, GFP_KERNEL); + s->base = kzalloc(sb->s_blocksize, GFP_KERNEL); /* assert(header == s->base) */ error = -ENOMEM; if (s->base == NULL) goto cleanup; - memset(s->base, 0, sb->s_blocksize); header(s->base)->h_magic = cpu_to_le32(EXT3_XATTR_MAGIC); header(s->base)->h_blocks = cpu_to_le32(1); header(s->base)->h_refcount = cpu_to_le32(1); diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index b74bf43..e906b65 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -20,6 +20,7 @@ #include <linux/quotaops.h> #include <linux/buffer_head.h> +#include "group.h" /* * balloc.c contains the blocks allocation and deallocation routines */ @@ -42,6 +43,94 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, } +/* Initializes an uninitialized block bitmap if given, and returns the + * number of blocks free in the group. */ +unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, + int block_group, struct ext4_group_desc *gdp) +{ + unsigned long start; + int bit, bit_max; + unsigned free_blocks, group_blocks; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (bh) { + J_ASSERT_BH(bh, buffer_locked(bh)); + + /* If checksum is bad mark all blocks used to prevent allocation + * essentially implementing a per-group read-only flag. */ + if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) { + ext4_error(sb, __FUNCTION__, + "Checksum bad for group %u\n", block_group); + gdp->bg_free_blocks_count = 0; + gdp->bg_free_inodes_count = 0; + gdp->bg_itable_unused = 0; + memset(bh->b_data, 0xff, sb->s_blocksize); + return 0; + } + memset(bh->b_data, 0, sb->s_blocksize); + } + + /* Check for superblock and gdt backups in this group */ + bit_max = ext4_bg_has_super(sb, block_group); + + if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) || + block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) * + sbi->s_desc_per_block) { + if (bit_max) { + bit_max += ext4_bg_num_gdb(sb, block_group); + bit_max += + le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks); + } + } else { /* For META_BG_BLOCK_GROUPS */ + int group_rel = (block_group - + le32_to_cpu(sbi->s_es->s_first_meta_bg)) % + EXT4_DESC_PER_BLOCK(sb); + if (group_rel == 0 || group_rel == 1 || + (group_rel == EXT4_DESC_PER_BLOCK(sb) - 1)) + bit_max += 1; + } + + if (block_group == sbi->s_groups_count - 1) { + /* + * Even though mke2fs always initialize first and last group + * if some other tool enabled the EXT4_BG_BLOCK_UNINIT we need + * to make sure we calculate the right free blocks + */ + group_blocks = ext4_blocks_count(sbi->s_es) - + le32_to_cpu(sbi->s_es->s_first_data_block) - + (EXT4_BLOCKS_PER_GROUP(sb) * (sbi->s_groups_count -1)); + } else { + group_blocks = EXT4_BLOCKS_PER_GROUP(sb); + } + + free_blocks = group_blocks - bit_max; + + if (bh) { + for (bit = 0; bit < bit_max; bit++) + ext4_set_bit(bit, bh->b_data); + + start = block_group * EXT4_BLOCKS_PER_GROUP(sb) + + le32_to_cpu(sbi->s_es->s_first_data_block); + + /* Set bits for block and inode bitmaps, and inode table */ + ext4_set_bit(ext4_block_bitmap(sb, gdp) - start, bh->b_data); + ext4_set_bit(ext4_inode_bitmap(sb, gdp) - start, bh->b_data); + for (bit = (ext4_inode_table(sb, gdp) - start), + bit_max = bit + sbi->s_itb_per_group; bit < bit_max; bit++) + ext4_set_bit(bit, bh->b_data); + + /* + * Also if the number of blocks within the group is + * less than the blocksize * 8 ( which is the size + * of bitmap ), set rest of the block bitmap to 1 + */ + mark_bitmap_end(group_blocks, sb->s_blocksize * 8, bh->b_data); + } + + return free_blocks - sbi->s_itb_per_group - 2; +} + + /* * The free blocks are managed by bitmaps. A file system contains several * blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap @@ -119,7 +208,7 @@ block_in_use(ext4_fsblk_t block, struct super_block *sb, unsigned char *map) * * Return buffer_head on success or NULL in case of failure. */ -static struct buffer_head * +struct buffer_head * read_block_bitmap(struct super_block *sb, unsigned int block_group) { int i; @@ -127,11 +216,24 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group) struct buffer_head * bh = NULL; ext4_fsblk_t bitmap_blk; - desc = ext4_get_group_desc (sb, block_group, NULL); + desc = ext4_get_group_desc(sb, block_group, NULL); if (!desc) return NULL; bitmap_blk = ext4_block_bitmap(sb, desc); - bh = sb_bread(sb, bitmap_blk); + if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { + bh = sb_getblk(sb, bitmap_blk); + if (!buffer_uptodate(bh)) { + lock_buffer(bh); + if (!buffer_uptodate(bh)) { + ext4_init_block_bitmap(sb, bh, block_group, + desc); + set_buffer_uptodate(bh); + } + unlock_buffer(bh); + } + } else { + bh = sb_bread(sb, bitmap_blk); + } if (!bh) ext4_error (sb, __FUNCTION__, "Cannot read block bitmap - " @@ -627,6 +729,7 @@ do_more: desc->bg_free_blocks_count = cpu_to_le16(le16_to_cpu(desc->bg_free_blocks_count) + group_freed); + desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc); spin_unlock(sb_bgl_lock(sbi, block_group)); percpu_counter_add(&sbi->s_freeblocks_counter, count); @@ -1685,8 +1788,11 @@ allocated: ret_block, goal_hits, goal_attempts); spin_lock(sb_bgl_lock(sbi, group_no)); + if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) + gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); gdp->bg_free_blocks_count = cpu_to_le16(le16_to_cpu(gdp->bg_free_blocks_count)-num); + gdp->bg_checksum = ext4_group_desc_csum(sbi, group_no, gdp); spin_unlock(sb_bgl_lock(sbi, group_no)); percpu_counter_sub(&sbi->s_freeblocks_counter, num); diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 0fb1e62..f612bef 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -47,9 +47,7 @@ const struct file_operations ext4_dir_operations = { .compat_ioctl = ext4_compat_ioctl, #endif .fsync = ext4_sync_file, /* BKL held */ -#ifdef CONFIG_EXT4_INDEX .release = ext4_release_dir, -#endif }; @@ -107,7 +105,6 @@ static int ext4_readdir(struct file * filp, sb = inode->i_sb; -#ifdef CONFIG_EXT4_INDEX if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_COMPAT_DIR_INDEX) && ((EXT4_I(inode)->i_flags & EXT4_INDEX_FL) || @@ -123,7 +120,6 @@ static int ext4_readdir(struct file * filp, */ EXT4_I(filp->f_path.dentry->d_inode)->i_flags &= ~EXT4_INDEX_FL; } -#endif stored = 0; offset = filp->f_pos & (sb->s_blocksize - 1); @@ -232,7 +228,6 @@ out: return ret; } -#ifdef CONFIG_EXT4_INDEX /* * These functions convert from the major/minor hash to an f_pos * value. @@ -518,5 +513,3 @@ static int ext4_release_dir (struct inode * inode, struct file * filp) return 0; } - -#endif diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 78beb09..8528774 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -33,7 +33,7 @@ #include <linux/fs.h> #include <linux/time.h> #include <linux/ext4_jbd2.h> -#include <linux/jbd.h> +#include <linux/jbd2.h> #include <linux/highuid.h> #include <linux/pagemap.h> #include <linux/quotaops.h> @@ -52,7 +52,7 @@ static ext4_fsblk_t ext_pblock(struct ext4_extent *ex) { ext4_fsblk_t block; - block = le32_to_cpu(ex->ee_start); + block = le32_to_cpu(ex->ee_start_lo); block |= ((ext4_fsblk_t) le16_to_cpu(ex->ee_start_hi) << 31) << 1; return block; } @@ -65,7 +65,7 @@ static ext4_fsblk_t idx_pblock(struct ext4_extent_idx *ix) { ext4_fsblk_t block; - block = le32_to_cpu(ix->ei_leaf); + block = le32_to_cpu(ix->ei_leaf_lo); block |= ((ext4_fsblk_t) le16_to_cpu(ix->ei_leaf_hi) << 31) << 1; return block; } @@ -77,7 +77,7 @@ static ext4_fsblk_t idx_pblock(struct ext4_extent_idx *ix) */ static void ext4_ext_store_pblock(struct ext4_extent *ex, ext4_fsblk_t pb) { - ex->ee_start = cpu_to_le32((unsigned long) (pb & 0xffffffff)); + ex->ee_start_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff)); ex->ee_start_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff); } @@ -88,7 +88,7 @@ static void ext4_ext_store_pblock(struct ext4_extent *ex, ext4_fsblk_t pb) */ static void ext4_idx_store_pblock(struct ext4_extent_idx *ix, ext4_fsblk_t pb) { - ix->ei_leaf = cpu_to_le32((unsigned long) (pb & 0xffffffff)); + ix->ei_leaf_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff)); ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff); } @@ -1409,8 +1409,7 @@ has_space: eh->eh_entries = cpu_to_le16(le16_to_cpu(eh->eh_entries)+1); nearex = path[depth].p_ext; nearex->ee_block = newext->ee_block; - nearex->ee_start = newext->ee_start; - nearex->ee_start_hi = newext->ee_start_hi; + ext4_ext_store_pblock(nearex, ext_pblock(newext)); nearex->ee_len = newext->ee_len; merge: @@ -2177,7 +2176,6 @@ int ext4_ext_convert_to_initialized(handle_t *handle, struct inode *inode, } /* ex2: iblock to iblock + maxblocks-1 : initialised */ ex2->ee_block = cpu_to_le32(iblock); - ex2->ee_start = cpu_to_le32(newblock); ext4_ext_store_pblock(ex2, newblock); ex2->ee_len = cpu_to_le16(allocated); if (ex2 != ex) diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 2a167d7..8d50879 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -47,7 +47,7 @@ int ext4_sync_file(struct file * file, struct dentry *dentry, int datasync) struct inode *inode = dentry->d_inode; int ret = 0; - J_ASSERT(ext4_journal_current_handle() == 0); + J_ASSERT(ext4_journal_current_handle() == NULL); /* * data=writeback: diff --git a/fs/ext4/group.h b/fs/ext4/group.h new file mode 100644 index 0000000..1577910 --- /dev/null +++ b/fs/ext4/group.h @@ -0,0 +1,27 @@ +/* + * linux/fs/ext4/group.h + * + * Copyright (C) 2007 Cluster File Systems, Inc + * + * Author: Andreas Dilger <adilger@clusterfs.com> + */ + +#ifndef _LINUX_EXT4_GROUP_H +#define _LINUX_EXT4_GROUP_H + +extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group, + struct ext4_group_desc *gdp); +extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group, + struct ext4_group_desc *gdp); +struct buffer_head *read_block_bitmap(struct super_block *sb, + unsigned int block_group); +extern unsigned ext4_init_block_bitmap(struct super_block *sb, + struct buffer_head *bh, int group, + struct ext4_group_desc *desc); +#define ext4_free_blocks_after_init(sb, group, desc) \ + ext4_init_block_bitmap(sb, NULL, group, desc) +extern unsigned ext4_init_inode_bitmap(struct super_block *sb, + struct buffer_head *bh, int group, + struct ext4_group_desc *desc); +extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap); +#endif /* _LINUX_EXT4_GROUP_H */ diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index d0c7793..c61f37f 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -28,6 +28,7 @@ #include "xattr.h" #include "acl.h" +#include "group.h" /* * ialloc.c contains the inodes allocation and deallocation routines @@ -43,6 +44,52 @@ * the free blocks count in the block. */ +/* + * To avoid calling the atomic setbit hundreds or thousands of times, we only + * need to use it within a single byte (to ensure we get endianness right). + * We can use memset for the rest of the bitmap as there are no other users. + */ +void mark_bitmap_end(int start_bit, int end_bit, char *bitmap) +{ + int i; + + if (start_bit >= end_bit) + return; + + ext4_debug("mark end bits +%d through +%d used\n", start_bit, end_bit); + for (i = start_bit; i < ((start_bit + 7) & ~7UL); i++) + ext4_set_bit(i, bitmap); + if (i < end_bit) + memset(bitmap + (i >> 3), 0xff, (end_bit - i) >> 3); +} + +/* Initializes an uninitialized inode bitmap */ +unsigned ext4_init_inode_bitmap(struct super_block *sb, + struct buffer_head *bh, int block_group, + struct ext4_group_desc *gdp) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + + J_ASSERT_BH(bh, buffer_locked(bh)); + + /* If checksum is bad mark all blocks and inodes use to prevent + * allocation, essentially implementing a per-group read-only flag. */ + if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) { + ext4_error(sb, __FUNCTION__, "Checksum bad for group %u\n", + block_group); + gdp->bg_free_blocks_count = 0; + gdp->bg_free_inodes_count = 0; + gdp->bg_itable_unused = 0; + memset(bh->b_data, 0xff, sb->s_blocksize); + return 0; + } + + memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8); + mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), EXT4_BLOCKS_PER_GROUP(sb), + bh->b_data); + + return EXT4_INODES_PER_GROUP(sb); +} /* * Read the inode allocation bitmap for a given block_group, reading @@ -59,8 +106,20 @@ read_inode_bitmap(struct super_block * sb, unsigned long block_group) desc = ext4_get_group_desc(sb, block_group, NULL); if (!desc) goto error_out; - - bh = sb_bread(sb, ext4_inode_bitmap(sb, desc)); + if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) { + bh = sb_getblk(sb, ext4_inode_bitmap(sb, desc)); + if (!buffer_uptodate(bh)) { + lock_buffer(bh); + if (!buffer_uptodate(bh)) { + ext4_init_inode_bitmap(sb, bh, block_group, + desc); + set_buffer_uptodate(bh); + } + unlock_buffer(bh); + } + } else { + bh = sb_bread(sb, ext4_inode_bitmap(sb, desc)); + } if (!bh) ext4_error(sb, "read_inode_bitmap", "Cannot read inode bitmap - " @@ -169,6 +228,8 @@ void ext4_free_inode (handle_t *handle, struct inode * inode) if (is_directory) gdp->bg_used_dirs_count = cpu_to_le16( le16_to_cpu(gdp->bg_used_dirs_count) - 1); + gdp->bg_checksum = ext4_group_desc_csum(sbi, + block_group, gdp); spin_unlock(sb_bgl_lock(sbi, block_group)); percpu_counter_inc(&sbi->s_freeinodes_counter); if (is_directory) @@ -435,7 +496,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode) struct ext4_sb_info *sbi; int err = 0; struct inode *ret; - int i; + int i, free = 0; /* Cannot create files in a deleted directory */ if (!dir || !dir->i_nlink) @@ -517,11 +578,13 @@ repeat_in_this_group: goto out; got: - ino += group * EXT4_INODES_PER_GROUP(sb) + 1; - if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) { - ext4_error (sb, "ext4_new_inode", - "reserved inode or inode > inodes count - " - "block_group = %d, inode=%lu", group, ino); + ino++; + if ((group == 0 && ino < EXT4_FIRST_INO(sb)) || + ino > EXT4_INODES_PER_GROUP(sb)) { + ext4_error(sb, __FUNCTION__, + "reserved inode or inode > inodes count - " + "block_group = %d, inode=%lu", group, + ino + group * EXT4_INODES_PER_GROUP(sb)); err = -EIO; goto fail; } @@ -529,13 +592,78 @@ got: BUFFER_TRACE(bh2, "get_write_access"); err = ext4_journal_get_write_access(handle, bh2); if (err) goto fail; + + /* We may have to initialize the block bitmap if it isn't already */ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM) && + gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { + struct buffer_head *block_bh = read_block_bitmap(sb, group); + + BUFFER_TRACE(block_bh, "get block bitmap access"); + err = ext4_journal_get_write_access(handle, block_bh); + if (err) { + brelse(block_bh); + goto fail; + } + + free = 0; + spin_lock(sb_bgl_lock(sbi, group)); + /* recheck and clear flag under lock if we still need to */ + if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { + gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); + free = ext4_free_blocks_after_init(sb, group, gdp); + gdp->bg_free_blocks_count = cpu_to_le16(free); + } + spin_unlock(sb_bgl_lock(sbi, group)); + + /* Don't need to dirty bitmap block if we didn't change it */ + if (free) { + BUFFER_TRACE(block_bh, "dirty block bitmap"); + err = ext4_journal_dirty_metadata(handle, block_bh); + } + + brelse(block_bh); + if (err) + goto fail; + } + spin_lock(sb_bgl_lock(sbi, group)); + /* If we didn't allocate from within the initialized part of the inode + * table then we need to initialize up to this inode. */ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) { + if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) { + gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT); + + /* When marking the block group with + * ~EXT4_BG_INODE_UNINIT we don't want to depend + * on the value of bg_itable_unsed even though + * mke2fs could have initialized the same for us. + * Instead we calculated the value below + */ + + free = 0; + } else { + free = EXT4_INODES_PER_GROUP(sb) - + le16_to_cpu(gdp->bg_itable_unused); + } + + /* + * Check the relative inode number against the last used + * relative inode number in this group. if it is greater + * we need to update the bg_itable_unused count + * + */ + if (ino > free) + gdp->bg_itable_unused = + cpu_to_le16(EXT4_INODES_PER_GROUP(sb) - ino); + } + gdp->bg_free_inodes_count = cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1); if (S_ISDIR(mode)) { gdp->bg_used_dirs_count = cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1); } + gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); spin_unlock(sb_bgl_lock(sbi, group)); BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata"); err = ext4_journal_dirty_metadata(handle, bh2); @@ -557,7 +685,7 @@ got: inode->i_gid = current->fsgid; inode->i_mode = mode; - inode->i_ino = ino; + inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb); /* 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 = ei->i_crtime = @@ -573,11 +701,6 @@ got: /* dirsync only applies to directories */ if (!S_ISDIR(mode)) ei->i_flags &= ~EXT4_DIRSYNC_FL; -#ifdef EXT4_FRAGMENTS - ei->i_faddr = 0; - ei->i_frag_no = 0; - ei->i_frag_size = 0; -#endif ei->i_file_acl = 0; ei->i_dir_acl = 0; ei->i_dtime = 0; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0df2b1e..5489703 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1027,7 +1027,7 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, } if (buffer_new(&dummy)) { J_ASSERT(create != 0); - J_ASSERT(handle != 0); + J_ASSERT(handle != NULL); /* * Now that we do not always journal data, we should @@ -2711,11 +2711,6 @@ void ext4_read_inode(struct inode * inode) } inode->i_blocks = le32_to_cpu(raw_inode->i_blocks); ei->i_flags = le32_to_cpu(raw_inode->i_flags); -#ifdef EXT4_FRAGMENTS - ei->i_faddr = le32_to_cpu(raw_inode->i_faddr); - ei->i_frag_no = raw_inode->i_frag; - ei->i_frag_size = raw_inode->i_fsize; -#endif ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl); if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_HURD)) @@ -2860,11 +2855,6 @@ static int ext4_do_update_inode(handle_t *handle, raw_inode->i_blocks = cpu_to_le32(inode->i_blocks); raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); raw_inode->i_flags = cpu_to_le32(ei->i_flags); -#ifdef EXT4_FRAGMENTS - raw_inode->i_faddr = cpu_to_le32(ei->i_faddr); - raw_inode->i_frag = ei->i_frag_no; - raw_inode->i_fsize = ei->i_frag_size; -#endif if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_HURD)) raw_inode->i_file_acl_high = @@ -3243,12 +3233,14 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) iloc, handle); if (ret) { EXT4_I(inode)->i_state |= EXT4_STATE_NO_EXPAND; - if (mnt_count != sbi->s_es->s_mnt_count) { + if (mnt_count != + le16_to_cpu(sbi->s_es->s_mnt_count)) { ext4_warning(inode->i_sb, __FUNCTION__, "Unable to expand inode %lu. Delete" " some EAs or run e2fsck.", inode->i_ino); - mnt_count = sbi->s_es->s_mnt_count; + mnt_count = + le16_to_cpu(sbi->s_es->s_mnt_count); } } } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 5fdb862..94ee6f3 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -144,7 +144,6 @@ struct dx_map_entry u16 size; }; -#ifdef CONFIG_EXT4_INDEX static inline unsigned dx_get_block (struct dx_entry *entry); static void dx_set_block (struct dx_entry *entry, unsigned value); static inline unsigned dx_get_hash (struct dx_entry *entry); @@ -766,8 +765,6 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, u32 block) dx_set_block(new, block); dx_set_count(entries, count + 1); } -#endif - static void ext4_update_dx_flag(struct inode *inode) { @@ -869,7 +866,6 @@ static struct buffer_head * ext4_find_entry (struct dentry *dentry, name = dentry->d_name.name; if (namelen > EXT4_NAME_LEN) return NULL; -#ifdef CONFIG_EXT4_INDEX if (is_dx(dir)) { bh = ext4_dx_find_entry(dentry, res_dir, &err); /* @@ -881,7 +877,6 @@ static struct buffer_head * ext4_find_entry (struct dentry *dentry, return bh; dxtrace(printk("ext4_find_entry: dx failed, falling back\n")); } -#endif nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb); start = EXT4_I(dir)->i_dir_start_lookup; if (start >= nblocks) @@ -957,7 +952,6 @@ cleanup_and_exit: return ret; } -#ifdef CONFIG_EXT4_INDEX static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry, struct ext4_dir_entry_2 **res_dir, int *err) { @@ -1025,7 +1019,6 @@ errout: dx_release (frames); return NULL; } -#endif static struct dentry *ext4_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd) { @@ -1121,7 +1114,6 @@ static inline void ext4_set_de_type(struct super_block *sb, de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT]; } -#ifdef CONFIG_EXT4_INDEX /* * Move count entries from end of map between two memory locations. * Returns pointer to last entry moved. @@ -1266,8 +1258,6 @@ errout: *error = err; return NULL; } -#endif - /* * Add a new entry into a directory (leaf) block. If de is non-NULL, @@ -1364,7 +1354,6 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, return 0; } -#ifdef CONFIG_EXT4_INDEX /* * This converts a one block unindexed directory to a 3 block indexed * directory, and adds the dentry to the indexed directory. @@ -1443,7 +1432,6 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, return add_dirent_to_buf(handle, dentry, inode, de, bh); } -#endif /* * ext4_add_entry() @@ -1464,9 +1452,7 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry, struct ext4_dir_entry_2 *de; struct super_block * sb; int retval; -#ifdef CONFIG_EXT4_INDEX int dx_fallback=0; -#endif unsigned blocksize; u32 block, blocks; @@ -1474,7 +1460,6 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry, blocksize = sb->s_blocksize; if (!dentry->d_name.len) return -EINVAL; -#ifdef CONFIG_EXT4_INDEX if (is_dx(dir)) { retval = ext4_dx_add_entry(handle, dentry, inode); if (!retval || (retval != ERR_BAD_DX_DIR)) @@ -1483,7 +1468,6 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry, dx_fallback++; ext4_mark_inode_dirty(handle, dir); } -#endif blocks = dir->i_size >> sb->s_blocksize_bits; for (block = 0, offset = 0; block < blocks; block++) { bh = ext4_bread(handle, dir, block, 0, &retval); @@ -1493,11 +1477,9 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry, if (retval != -ENOSPC) return retval; -#ifdef CONFIG_EXT4_INDEX if (blocks == 1 && !dx_fallback && EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) return make_indexed_dir(handle, dentry, inode, bh); -#endif brelse(bh); } bh = ext4_append(handle, dir, &block, &retval); @@ -1509,7 +1491,6 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry, return add_dirent_to_buf(handle, dentry, inode, de, bh); } -#ifdef CONFIG_EXT4_INDEX /* * Returns 0 for success, or a negative error value */ @@ -1644,7 +1625,6 @@ cleanup: dx_release(frames); return err; } -#endif /* * ext4_delete_entry deletes a directory entry by merging it with the diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 472fc0d..bd8a52b 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -16,6 +16,7 @@ #include <linux/errno.h> #include <linux/slab.h> +#include "group.h" #define outside(b, first, last) ((b) < (first) || (b) >= (last)) #define inside(b, first, last) ((b) >= (first) && (b) < (last)) @@ -140,22 +141,29 @@ static struct buffer_head *bclean(handle_t *handle, struct super_block *sb, } /* - * To avoid calling the atomic setbit hundreds or thousands of times, we only - * need to use it within a single byte (to ensure we get endianness right). - * We can use memset for the rest of the bitmap as there are no other users. + * If we have fewer than thresh credits, extend by EXT4_MAX_TRANS_DATA. + * If that fails, restart the transaction & regain write access for the + * buffer head which is used for block_bitmap modifications. */ -static void mark_bitmap_end(int start_bit, int end_bit, char *bitmap) +static int extend_or_restart_transaction(handle_t *handle, int thresh, + struct buffer_head *bh) { - int i; + int err; + + if (handle->h_buffer_credits >= thresh) + return 0; - if (start_bit >= end_bit) - return; + err = ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA); + if (err < 0) + return err; + if (err) { + if ((err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA))) + return err; + if ((err = ext4_journal_get_write_access(handle, bh))) + return err; + } - ext4_debug("mark end bits +%d through +%d used\n", start_bit, end_bit); - for (i = start_bit; i < ((start_bit + 7) & ~7UL); i++) - ext4_set_bit(i, bitmap); - if (i < end_bit) - memset(bitmap + (i >> 3), 0xff, (end_bit - i) >> 3); + return 0; } /* @@ -180,8 +188,9 @@ static int setup_new_group_blocks(struct super_block *sb, int i; int err = 0, err2; - handle = ext4_journal_start_sb(sb, reserved_gdb + gdblocks + - 2 + sbi->s_itb_per_group); + /* This transaction may be extended/restarted along the way */ + handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA); + if (IS_ERR(handle)) return PTR_ERR(handle); @@ -208,6 +217,9 @@ static int setup_new_group_blocks(struct super_block *sb, ext4_debug("update backup group %#04lx (+%d)\n", block, bit); + if ((err = extend_or_restart_transaction(handle, 1, bh))) + goto exit_bh; + gdb = sb_getblk(sb, block); if (!gdb) { err = -EIO; @@ -217,10 +229,10 @@ static int setup_new_group_blocks(struct super_block *sb, brelse(gdb); goto exit_bh; } - lock_buffer(bh); - memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, bh->b_size); + lock_buffer(gdb); + memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, gdb->b_size); set_buffer_uptodate(gdb); - unlock_buffer(bh); + unlock_buffer(gdb); ext4_journal_dirty_metadata(handle, gdb); ext4_set_bit(bit, bh->b_data); brelse(gdb); @@ -233,6 +245,9 @@ static int setup_new_group_blocks(struct super_block *sb, ext4_debug("clear reserved block %#04lx (+%d)\n", block, bit); + if ((err = extend_or_restart_transaction(handle, 1, bh))) + goto exit_bh; + if (IS_ERR(gdb = bclean(handle, sb, block))) { err = PTR_ERR(bh); goto exit_bh; @@ -254,6 +269,10 @@ static int setup_new_group_blocks(struct super_block *sb, struct buffer_head *it; ext4_debug("clear inode block %#04lx (+%d)\n", block, bit); + + if ((err = extend_or_restart_transaction(handle, 1, bh))) + goto exit_bh; + if (IS_ERR(it = bclean(handle, sb, block))) { err = PTR_ERR(it); goto exit_bh; @@ -262,6 +281,10 @@ static int setup_new_group_blocks(struct super_block *sb, brelse(it); ext4_set_bit(bit, bh->b_data); } + + if ((err = extend_or_restart_transaction(handle, 2, bh))) + goto exit_bh; + mark_bitmap_end(input->blocks_count, EXT4_BLOCKS_PER_GROUP(sb), bh->b_data); ext4_journal_dirty_metadata(handle, bh); @@ -289,7 +312,6 @@ exit_journal: return err; } - /* * Iterate through the groups which hold BACKUP superblock/GDT copies in an * ext4 filesystem. The counters should be initialized to 1, 5, and 7 before @@ -842,6 +864,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) ext4_inode_table_set(sb, gdp, input->inode_table); /* LV FIXME */ gdp->bg_free_blocks_count = cpu_to_le16(input->free_blocks_count); gdp->bg_free_inodes_count = cpu_to_le16(EXT4_INODES_PER_GROUP(sb)); + gdp->bg_checksum = ext4_group_desc_csum(sbi, input->group, gdp); /* * Make the new blocks and inodes valid next. We do this before diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 4c8d31c..b11e9e2 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -37,12 +37,14 @@ #include <linux/quotaops.h> #include <linux/seq_file.h> #include <linux/log2.h> +#include <linux/crc16.h> #include <asm/uaccess.h> #include "xattr.h" #include "acl.h" #include "namei.h" +#include "group.h" static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); @@ -68,31 +70,31 @@ static void ext4_write_super_lockfs(struct super_block *sb); ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, struct ext4_group_desc *bg) { - return le32_to_cpu(bg->bg_block_bitmap) | + return le32_to_cpu(bg->bg_block_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0); + (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, struct ext4_group_desc *bg) { - return le32_to_cpu(bg->bg_inode_bitmap) | + return le32_to_cpu(bg->bg_inode_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0); + (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_table(struct super_block *sb, struct ext4_group_desc *bg) { - return le32_to_cpu(bg->bg_inode_table) | + return le32_to_cpu(bg->bg_inode_table_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0); + (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0); } void ext4_block_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { - bg->bg_block_bitmap = cpu_to_le32((u32)blk); + bg->bg_block_bitmap_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_block_bitmap_hi = cpu_to_le32(blk >> 32); } @@ -100,7 +102,7 @@ void ext4_block_bitmap_set(struct super_block *sb, void ext4_inode_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { - bg->bg_inode_bitmap = cpu_to_le32((u32)blk); + bg->bg_inode_bitmap_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_inode_bitmap_hi = cpu_to_le32(blk >> 32); } @@ -108,7 +110,7 @@ void ext4_inode_bitmap_set(struct super_block *sb, void ext4_inode_table_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { - bg->bg_inode_table = cpu_to_le32((u32)blk); + bg->bg_inode_table_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_inode_table_hi = cpu_to_le32(blk >> 32); } @@ -1037,7 +1039,7 @@ static int parse_options (char *options, struct super_block *sb, if (option < 0) return 0; if (option == 0) - option = JBD_DEFAULT_MAX_COMMIT_AGE; + option = JBD2_DEFAULT_MAX_COMMIT_AGE; sbi->s_commit_interval = HZ * option; break; case Opt_data_journal: @@ -1308,6 +1310,43 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, return res; } +__le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, + struct ext4_group_desc *gdp) +{ + __u16 crc = 0; + + if (sbi->s_es->s_feature_ro_compat & + cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) { + int offset = offsetof(struct ext4_group_desc, bg_checksum); + __le32 le_group = cpu_to_le32(block_group); + + crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid)); + crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group)); + crc = crc16(crc, (__u8 *)gdp, offset); + offset += sizeof(gdp->bg_checksum); /* skip checksum */ + /* for checksum of struct ext4_group_desc do the rest...*/ + if ((sbi->s_es->s_feature_incompat & + cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT)) && + offset < le16_to_cpu(sbi->s_es->s_desc_size)) + crc = crc16(crc, (__u8 *)gdp + offset, + le16_to_cpu(sbi->s_es->s_desc_size) - + offset); + } + + return cpu_to_le16(crc); +} + +int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group, + struct ext4_group_desc *gdp) +{ + if ((sbi->s_es->s_feature_ro_compat & + cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) && + (gdp->bg_checksum != ext4_group_desc_csum(sbi, block_group, gdp))) + return 0; + + return 1; +} + /* Called at mount-time, super-block is locked */ static int ext4_check_descriptors (struct super_block * sb) { @@ -1319,13 +1358,17 @@ static int ext4_check_descriptors (struct super_block * sb) ext4_fsblk_t inode_table; struct ext4_group_desc * gdp = NULL; int desc_block = 0; + int flexbg_flag = 0; int i; + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) + flexbg_flag = 1; + ext4_debug ("Checking group descriptors"); for (i = 0; i < sbi->s_groups_count; i++) { - if (i == sbi->s_groups_count - 1) + if (i == sbi->s_groups_count - 1 || flexbg_flag) last_block = ext4_blocks_count(sbi->s_es) - 1; else last_block = first_block + @@ -1362,7 +1405,16 @@ static int ext4_check_descriptors (struct super_block * sb) i, inode_table); return 0; } - first_block += EXT4_BLOCKS_PER_GROUP(sb); + if (!ext4_group_desc_csum_verify(sbi, i, gdp)) { + ext4_error(sb, __FUNCTION__, + "Checksum for group %d failed (%u!=%u)\n", i, + le16_to_cpu(ext4_group_desc_csum(sbi, i, + gdp)), + le16_to_cpu(gdp->bg_checksum)); + return 0; + } + if (!flexbg_flag) + first_block += EXT4_BLOCKS_PER_GROUP(sb); gdp = (struct ext4_group_desc *) ((__u8 *)gdp + EXT4_DESC_SIZE(sb)); } @@ -1726,14 +1778,6 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) sb->s_time_gran = 1 << (EXT4_EPOCH_BITS - 2); } - sbi->s_frag_size = EXT4_MIN_FRAG_SIZE << - le32_to_cpu(es->s_log_frag_size); - if (blocksize != sbi->s_frag_size) { - printk(KERN_ERR - "EXT4-fs: fragsize %lu != blocksize %u (unsupported)\n", - sbi->s_frag_size, blocksize); - goto failed_mount; - } sbi->s_desc_size = le16_to_cpu(es->s_desc_size); if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) { if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT || @@ -1747,7 +1791,6 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) } else sbi->s_desc_size = EXT4_MIN_DESC_SIZE; sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); - sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); if (EXT4_INODE_SIZE(sb) == 0) goto cantfind_ext4; @@ -1771,12 +1814,6 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) sbi->s_blocks_per_group); goto failed_mount; } - if (sbi->s_frags_per_group > blocksize * 8) { - printk (KERN_ERR - "EXT4-fs: #fragments per group too big: %lu\n", - sbi->s_frags_per_group); - goto failed_mount; - } if (sbi->s_inodes_per_group > blocksize * 8) { printk (KERN_ERR "EXT4-fs: #inodes per group too big: %lu\n", @@ -2630,7 +2667,7 @@ static int ext4_statfs (struct dentry * dentry, struct kstatfs * buf) if (test_opt(sb, MINIX_DF)) { sbi->s_overhead_last = 0; - } else if (sbi->s_blocks_last != le32_to_cpu(es->s_blocks_count)) { + } else if (sbi->s_blocks_last != ext4_blocks_count(es)) { unsigned long ngroups = sbi->s_groups_count, i; ext4_fsblk_t overhead = 0; smp_rmb(); @@ -2665,14 +2702,14 @@ static int ext4_statfs (struct dentry * dentry, struct kstatfs * buf) overhead += ngroups * (2 + sbi->s_itb_per_group); sbi->s_overhead_last = overhead; smp_wmb(); - sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count); + sbi->s_blocks_last = ext4_blocks_count(es); } buf->f_type = EXT4_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last; buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter); - es->s_free_blocks_count = cpu_to_le32(buf->f_bfree); + ext4_free_blocks_count_set(es, buf->f_bfree); buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es); if (buf->f_bfree < ext4_r_blocks_count(es)) buf->f_bavail = 0; diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index b10d68f..8638730 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -750,12 +750,11 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, } } else { /* Allocate a buffer where we construct the new block. */ - s->base = kmalloc(sb->s_blocksize, GFP_KERNEL); + s->base = kzalloc(sb->s_blocksize, GFP_KERNEL); /* assert(header == s->base) */ error = -ENOMEM; if (s->base == NULL) goto cleanup; - memset(s->base, 0, sb->s_blocksize); header(s->base)->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); header(s->base)->h_blocks = cpu_to_le32(1); header(s->base)->h_refcount = cpu_to_le32(1); @@ -1121,7 +1120,7 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, int total_ino, total_blk; void *base, *start, *end; int extra_isize = 0, error = 0, tried_min_extra_isize = 0; - int s_min_extra_isize = EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize; + int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize); down_write(&EXT4_I(inode)->xattr_sem); retry: @@ -1293,7 +1292,7 @@ retry: i.name = b_entry_name; i.value = buffer; - i.value_len = cpu_to_le32(size); + i.value_len = size; error = ext4_xattr_block_find(inode, &i, bs); if (error) goto cleanup; @@ -18,6 +18,7 @@ #include <linux/ptrace.h> #include <linux/signal.h> #include <linux/rcupdate.h> +#include <linux/pid_namespace.h> #include <asm/poll.h> #include <asm/siginfo.h> @@ -292,7 +293,7 @@ int f_setown(struct file *filp, unsigned long arg, int force) who = -who; } rcu_read_lock(); - pid = find_pid(who); + pid = find_vpid(who); result = __f_setown(filp, pid, type, force); rcu_read_unlock(); return result; @@ -308,7 +309,7 @@ pid_t f_getown(struct file *filp) { pid_t pid; read_lock(&filp->f_owner.lock); - pid = pid_nr(filp->f_owner.pid); + pid = pid_nr_ns(filp->f_owner.pid, current->nsproxy->pid_ns); if (filp->f_owner.pid_type == PIDTYPE_PGID) pid = -pid; read_unlock(&filp->f_owner.lock); diff --git a/fs/file_table.c b/fs/file_table.c index 3176fef..664e3f2 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -323,12 +323,11 @@ void file_kill(struct file *file) int fs_may_remount_ro(struct super_block *sb) { - struct list_head *p; + struct file *file; /* Check that no files are currently opened for writing. */ file_list_lock(); - list_for_each(p, &sb->s_files) { - struct file *file = list_entry(p, struct file, f_u.fu_list); + list_for_each_entry(file, &sb->s_files, f_u.fu_list) { struct inode *inode = file->f_path.dentry->d_inode; /* File with pending delete? */ diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 686734f..0fca820 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -89,7 +89,7 @@ void __mark_inode_dirty(struct inode *inode, int flags) if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) printk(KERN_DEBUG "%s(%d): dirtied inode %lu (%s) on %s\n", - current->comm, current->pid, inode->i_ino, + current->comm, task_pid_nr(current), inode->i_ino, name, inode->i_sb->s_id); } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index d1acab9..3763757 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -63,13 +63,21 @@ static u64 time_to_jiffies(unsigned long sec, unsigned long nsec) * Set dentry and possibly attribute timeouts from the lookup/mk* * replies */ -static void fuse_change_timeout(struct dentry *entry, struct fuse_entry_out *o) +static void fuse_change_entry_timeout(struct dentry *entry, + struct fuse_entry_out *o) { fuse_dentry_settime(entry, time_to_jiffies(o->entry_valid, o->entry_valid_nsec)); - if (entry->d_inode) - get_fuse_inode(entry->d_inode)->i_time = - time_to_jiffies(o->attr_valid, o->attr_valid_nsec); +} + +static u64 attr_timeout(struct fuse_attr_out *o) +{ + return time_to_jiffies(o->attr_valid, o->attr_valid_nsec); +} + +static u64 entry_attr_timeout(struct fuse_entry_out *o) +{ + return time_to_jiffies(o->attr_valid, o->attr_valid_nsec); } /* @@ -108,13 +116,19 @@ static void fuse_lookup_init(struct fuse_req *req, struct inode *dir, struct dentry *entry, struct fuse_entry_out *outarg) { + struct fuse_conn *fc = get_fuse_conn(dir); + + memset(outarg, 0, sizeof(struct fuse_entry_out)); req->in.h.opcode = FUSE_LOOKUP; req->in.h.nodeid = get_node_id(dir); req->in.numargs = 1; req->in.args[0].size = entry->d_name.len + 1; req->in.args[0].value = entry->d_name.name; req->out.numargs = 1; - req->out.args[0].size = sizeof(struct fuse_entry_out); + if (fc->minor < 9) + req->out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE; + else + req->out.args[0].size = sizeof(struct fuse_entry_out); req->out.args[0].value = outarg; } @@ -140,6 +154,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) struct fuse_req *req; struct fuse_req *forget_req; struct dentry *parent; + u64 attr_version; /* For negative dentries, always do a fresh lookup */ if (!inode) @@ -156,6 +171,10 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) return 0; } + spin_lock(&fc->lock); + attr_version = fc->attr_version; + spin_unlock(&fc->lock); + parent = dget_parent(entry); fuse_lookup_init(req, parent->d_inode, entry, &outarg); request_send(fc, req); @@ -180,8 +199,10 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) if (err || (outarg.attr.mode ^ inode->i_mode) & S_IFMT) return 0; - fuse_change_attributes(inode, &outarg.attr); - fuse_change_timeout(entry, &outarg); + fuse_change_attributes(inode, &outarg.attr, + entry_attr_timeout(&outarg), + attr_version); + fuse_change_entry_timeout(entry, &outarg); } return 1; } @@ -228,6 +249,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, struct fuse_conn *fc = get_fuse_conn(dir); struct fuse_req *req; struct fuse_req *forget_req; + u64 attr_version; if (entry->d_name.len > FUSE_NAME_MAX) return ERR_PTR(-ENAMETOOLONG); @@ -242,6 +264,10 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, return ERR_PTR(PTR_ERR(forget_req)); } + spin_lock(&fc->lock); + attr_version = fc->attr_version; + spin_unlock(&fc->lock); + fuse_lookup_init(req, dir, entry, &outarg); request_send(fc, req); err = req->out.h.error; @@ -253,7 +279,8 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, err = -EIO; if (!err && outarg.nodeid) { inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation, - &outarg.attr); + &outarg.attr, entry_attr_timeout(&outarg), + attr_version); if (!inode) { fuse_send_forget(fc, forget_req, outarg.nodeid, 1); return ERR_PTR(-ENOMEM); @@ -276,7 +303,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, entry->d_op = &fuse_dentry_operations; if (!err) - fuse_change_timeout(entry, &outarg); + fuse_change_entry_timeout(entry, &outarg); else fuse_invalidate_entry_cache(entry); return NULL; @@ -335,6 +362,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, flags &= ~O_NOCTTY; memset(&inarg, 0, sizeof(inarg)); + memset(&outentry, 0, sizeof(outentry)); inarg.flags = flags; inarg.mode = mode; req->in.h.opcode = FUSE_CREATE; @@ -345,7 +373,10 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, req->in.args[1].size = entry->d_name.len + 1; req->in.args[1].value = entry->d_name.name; req->out.numargs = 2; - req->out.args[0].size = sizeof(outentry); + if (fc->minor < 9) + req->out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE; + else + req->out.args[0].size = sizeof(outentry); req->out.args[0].value = &outentry; req->out.args[1].size = sizeof(outopen); req->out.args[1].value = &outopen; @@ -363,7 +394,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, fuse_put_request(fc, req); inode = fuse_iget(dir->i_sb, outentry.nodeid, outentry.generation, - &outentry.attr); + &outentry.attr, entry_attr_timeout(&outentry), 0); if (!inode) { flags &= ~(O_CREAT | O_EXCL | O_TRUNC); ff->fh = outopen.fh; @@ -373,7 +404,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, } fuse_put_request(fc, forget_req); d_instantiate(entry, inode); - fuse_change_timeout(entry, &outentry); + fuse_change_entry_timeout(entry, &outentry); file = lookup_instantiate_filp(nd, entry, generic_file_open); if (IS_ERR(file)) { ff->fh = outopen.fh; @@ -410,9 +441,13 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req, return PTR_ERR(forget_req); } + memset(&outarg, 0, sizeof(outarg)); req->in.h.nodeid = get_node_id(dir); req->out.numargs = 1; - req->out.args[0].size = sizeof(outarg); + if (fc->minor < 9) + req->out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE; + else + req->out.args[0].size = sizeof(outarg); req->out.args[0].value = &outarg; request_send(fc, req); err = req->out.h.error; @@ -428,7 +463,7 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req, goto out_put_forget_req; inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation, - &outarg.attr); + &outarg.attr, entry_attr_timeout(&outarg), 0); if (!inode) { fuse_send_forget(fc, forget_req, outarg.nodeid, 1); return -ENOMEM; @@ -451,7 +486,7 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req, } else d_instantiate(entry, inode); - fuse_change_timeout(entry, &outarg); + fuse_change_entry_timeout(entry, &outarg); fuse_invalidate_attr(dir); return 0; @@ -663,52 +698,84 @@ static int fuse_link(struct dentry *entry, struct inode *newdir, return err; } -static int fuse_do_getattr(struct inode *inode) +static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr, + struct kstat *stat) +{ + stat->dev = inode->i_sb->s_dev; + stat->ino = attr->ino; + stat->mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777); + stat->nlink = attr->nlink; + stat->uid = attr->uid; + stat->gid = attr->gid; + stat->rdev = inode->i_rdev; + stat->atime.tv_sec = attr->atime; + stat->atime.tv_nsec = attr->atimensec; + stat->mtime.tv_sec = attr->mtime; + stat->mtime.tv_nsec = attr->mtimensec; + stat->ctime.tv_sec = attr->ctime; + stat->ctime.tv_nsec = attr->ctimensec; + stat->size = attr->size; + stat->blocks = attr->blocks; + stat->blksize = (1 << inode->i_blkbits); +} + +static int fuse_do_getattr(struct inode *inode, struct kstat *stat, + struct file *file) { int err; - struct fuse_attr_out arg; + struct fuse_getattr_in inarg; + struct fuse_attr_out outarg; struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_req *req = fuse_get_req(fc); + struct fuse_req *req; + u64 attr_version; + + req = fuse_get_req(fc); if (IS_ERR(req)) return PTR_ERR(req); + spin_lock(&fc->lock); + attr_version = fc->attr_version; + spin_unlock(&fc->lock); + + memset(&inarg, 0, sizeof(inarg)); + memset(&outarg, 0, sizeof(outarg)); + /* Directories have separate file-handle space */ + if (file && S_ISREG(inode->i_mode)) { + struct fuse_file *ff = file->private_data; + + inarg.getattr_flags |= FUSE_GETATTR_FH; + inarg.fh = ff->fh; + } req->in.h.opcode = FUSE_GETATTR; req->in.h.nodeid = get_node_id(inode); + req->in.numargs = 1; + req->in.args[0].size = sizeof(inarg); + req->in.args[0].value = &inarg; req->out.numargs = 1; - req->out.args[0].size = sizeof(arg); - req->out.args[0].value = &arg; + if (fc->minor < 9) + req->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE; + else + req->out.args[0].size = sizeof(outarg); + req->out.args[0].value = &outarg; request_send(fc, req); err = req->out.h.error; fuse_put_request(fc, req); if (!err) { - if ((inode->i_mode ^ arg.attr.mode) & S_IFMT) { + if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) { make_bad_inode(inode); err = -EIO; } else { - struct fuse_inode *fi = get_fuse_inode(inode); - fuse_change_attributes(inode, &arg.attr); - fi->i_time = time_to_jiffies(arg.attr_valid, - arg.attr_valid_nsec); + fuse_change_attributes(inode, &outarg.attr, + attr_timeout(&outarg), + attr_version); + if (stat) + fuse_fillattr(inode, &outarg.attr, stat); } } return err; } /* - * Check if attributes are still valid, and if not send a GETATTR - * request to refresh them. - */ -static int fuse_refresh_attributes(struct inode *inode) -{ - struct fuse_inode *fi = get_fuse_inode(inode); - - if (fi->i_time < get_jiffies_64()) - return fuse_do_getattr(inode); - else - return 0; -} - -/* * Calling into a user-controlled filesystem gives the filesystem * daemon ptrace-like capabilities over the requester process. This * means, that the filesystem daemon is able to record the exact @@ -721,7 +788,7 @@ static int fuse_refresh_attributes(struct inode *inode) * for which the owner of the mount has ptrace privilege. This * excludes processes started by other users, suid or sgid processes. */ -static int fuse_allow_task(struct fuse_conn *fc, struct task_struct *task) +int fuse_allow_task(struct fuse_conn *fc, struct task_struct *task) { if (fc->flags & FUSE_ALLOW_OTHER) return 1; @@ -795,11 +862,14 @@ static int fuse_permission(struct inode *inode, int mask, struct nameidata *nd) */ if ((fc->flags & FUSE_DEFAULT_PERMISSIONS) || ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) { - err = fuse_refresh_attributes(inode); - if (err) - return err; + struct fuse_inode *fi = get_fuse_inode(inode); + if (fi->i_time < get_jiffies_64()) { + err = fuse_do_getattr(inode, NULL, NULL); + if (err) + return err; - refreshed = true; + refreshed = true; + } } if (fc->flags & FUSE_DEFAULT_PERMISSIONS) { @@ -809,7 +879,7 @@ static int fuse_permission(struct inode *inode, int mask, struct nameidata *nd) attributes. This is also needed, because the root node will at first have no permissions */ if (err == -EACCES && !refreshed) { - err = fuse_do_getattr(inode); + err = fuse_do_getattr(inode, NULL, NULL); if (!err) err = generic_permission(inode, mask, NULL); } @@ -825,7 +895,7 @@ static int fuse_permission(struct inode *inode, int mask, struct nameidata *nd) if (refreshed) return -EACCES; - err = fuse_do_getattr(inode); + err = fuse_do_getattr(inode, NULL, NULL); if (!err && !(inode->i_mode & S_IXUGO)) return -EACCES; } @@ -962,6 +1032,20 @@ static int fuse_dir_fsync(struct file *file, struct dentry *de, int datasync) return file ? fuse_fsync_common(file, de, datasync, 1) : 0; } +static bool update_mtime(unsigned ivalid) +{ + /* Always update if mtime is explicitly set */ + if (ivalid & ATTR_MTIME_SET) + return true; + + /* If it's an open(O_TRUNC) or an ftruncate(), don't update */ + if ((ivalid & ATTR_SIZE) && (ivalid & (ATTR_OPEN | ATTR_FILE))) + return false; + + /* In all other cases update */ + return true; +} + static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg) { unsigned ivalid = iattr->ia_valid; @@ -974,16 +1058,19 @@ static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg) arg->valid |= FATTR_GID, arg->gid = iattr->ia_gid; if (ivalid & ATTR_SIZE) arg->valid |= FATTR_SIZE, arg->size = iattr->ia_size; - /* You can only _set_ these together (they may change by themselves) */ - if ((ivalid & (ATTR_ATIME | ATTR_MTIME)) == (ATTR_ATIME | ATTR_MTIME)) { - arg->valid |= FATTR_ATIME | FATTR_MTIME; + if (ivalid & ATTR_ATIME) { + arg->valid |= FATTR_ATIME; arg->atime = iattr->ia_atime.tv_sec; - arg->mtime = iattr->ia_mtime.tv_sec; + arg->atimensec = iattr->ia_atime.tv_nsec; + if (!(ivalid & ATTR_ATIME_SET)) + arg->valid |= FATTR_ATIME_NOW; } - if (ivalid & ATTR_FILE) { - struct fuse_file *ff = iattr->ia_file->private_data; - arg->valid |= FATTR_FH; - arg->fh = ff->fh; + if ((ivalid & ATTR_MTIME) && update_mtime(ivalid)) { + arg->valid |= FATTR_MTIME; + arg->mtime = iattr->ia_mtime.tv_sec; + arg->mtimensec = iattr->ia_mtime.tv_nsec; + if (!(ivalid & ATTR_MTIME_SET)) + arg->valid |= FATTR_MTIME_NOW; } } @@ -995,22 +1082,28 @@ static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg) * vmtruncate() doesn't allow for this case, so do the rlimit checking * and the actual truncation by hand. */ -static int fuse_setattr(struct dentry *entry, struct iattr *attr) +static int fuse_do_setattr(struct dentry *entry, struct iattr *attr, + struct file *file) { struct inode *inode = entry->d_inode; struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_req *req; struct fuse_setattr_in inarg; struct fuse_attr_out outarg; int err; + if (!fuse_allow_task(fc, current)) + return -EACCES; + if (fc->flags & FUSE_DEFAULT_PERMISSIONS) { err = inode_change_ok(inode, attr); if (err) return err; } + if ((attr->ia_valid & ATTR_OPEN) && fc->atomic_o_trunc) + return 0; + if (attr->ia_valid & ATTR_SIZE) { unsigned long limit; if (IS_SWAPFILE(inode)) @@ -1027,14 +1120,28 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr) return PTR_ERR(req); memset(&inarg, 0, sizeof(inarg)); + memset(&outarg, 0, sizeof(outarg)); iattr_to_fattr(attr, &inarg); + if (file) { + struct fuse_file *ff = file->private_data; + inarg.valid |= FATTR_FH; + inarg.fh = ff->fh; + } + if (attr->ia_valid & ATTR_SIZE) { + /* For mandatory locking in truncate */ + inarg.valid |= FATTR_LOCKOWNER; + inarg.lock_owner = fuse_lock_owner_id(fc, current->files); + } req->in.h.opcode = FUSE_SETATTR; req->in.h.nodeid = get_node_id(inode); req->in.numargs = 1; req->in.args[0].size = sizeof(inarg); req->in.args[0].value = &inarg; req->out.numargs = 1; - req->out.args[0].size = sizeof(outarg); + if (fc->minor < 9) + req->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE; + else + req->out.args[0].size = sizeof(outarg); req->out.args[0].value = &outarg; request_send(fc, req); err = req->out.h.error; @@ -1050,11 +1157,18 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr) return -EIO; } - fuse_change_attributes(inode, &outarg.attr); - fi->i_time = time_to_jiffies(outarg.attr_valid, outarg.attr_valid_nsec); + fuse_change_attributes(inode, &outarg.attr, attr_timeout(&outarg), 0); return 0; } +static int fuse_setattr(struct dentry *entry, struct iattr *attr) +{ + if (attr->ia_valid & ATTR_FILE) + return fuse_do_setattr(entry, attr, attr->ia_file); + else + return fuse_do_setattr(entry, attr, NULL); +} + static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry, struct kstat *stat) { @@ -1066,8 +1180,10 @@ static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry, if (!fuse_allow_task(fc, current)) return -EACCES; - err = fuse_refresh_attributes(inode); - if (!err) { + if (fi->i_time < get_jiffies_64()) + err = fuse_do_getattr(inode, stat, NULL); + else { + err = 0; generic_fillattr(inode, stat); stat->mode = fi->orig_i_mode; } @@ -1172,6 +1288,9 @@ static ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size) struct fuse_getxattr_out outarg; ssize_t ret; + if (!fuse_allow_task(fc, current)) + return -EACCES; + if (fc->no_listxattr) return -EOPNOTSUPP; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index c4b98c0..0fcdba9 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -28,7 +28,9 @@ static int fuse_send_open(struct inode *inode, struct file *file, int isdir, return PTR_ERR(req); memset(&inarg, 0, sizeof(inarg)); - inarg.flags = file->f_flags & ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); + inarg.flags = file->f_flags & ~(O_CREAT | O_EXCL | O_NOCTTY); + if (!fc->atomic_o_trunc) + inarg.flags &= ~O_TRUNC; req->in.h.opcode = isdir ? FUSE_OPENDIR : FUSE_OPEN; req->in.h.nodeid = get_node_id(inode); req->in.numargs = 1; @@ -54,6 +56,7 @@ struct fuse_file *fuse_file_alloc(void) kfree(ff); ff = NULL; } + INIT_LIST_HEAD(&ff->write_entry); atomic_set(&ff->count, 0); } return ff; @@ -148,12 +151,18 @@ int fuse_release_common(struct inode *inode, struct file *file, int isdir) { struct fuse_file *ff = file->private_data; if (ff) { + struct fuse_conn *fc = get_fuse_conn(inode); + fuse_release_fill(ff, get_node_id(inode), file->f_flags, isdir ? FUSE_RELEASEDIR : FUSE_RELEASE); /* Hold vfsmount and dentry until release is finished */ ff->reserved_req->vfsmount = mntget(file->f_path.mnt); ff->reserved_req->dentry = dget(file->f_path.dentry); + + spin_lock(&fc->lock); + list_del(&ff->write_entry); + spin_unlock(&fc->lock); /* * Normally this will send the RELEASE request, * however if some asynchronous READ or WRITE requests @@ -180,7 +189,7 @@ static int fuse_release(struct inode *inode, struct file *file) * Scramble the ID space with XTEA, so that the value of the files_struct * pointer is not exposed to userspace. */ -static u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id) +u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id) { u32 *k = fc->scramble_key; u64 v = (unsigned long) id; @@ -299,11 +308,19 @@ void fuse_read_fill(struct fuse_req *req, struct fuse_file *ff, } static size_t fuse_send_read(struct fuse_req *req, struct file *file, - struct inode *inode, loff_t pos, size_t count) + struct inode *inode, loff_t pos, size_t count, + fl_owner_t owner) { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_file *ff = file->private_data; + fuse_read_fill(req, ff, inode, pos, count, FUSE_READ); + if (owner != NULL) { + struct fuse_read_in *inarg = &req->misc.read_in; + + inarg->read_flags |= FUSE_READ_LOCKOWNER; + inarg->lock_owner = fuse_lock_owner_id(fc, owner); + } request_send(fc, req); return req->out.args[0].size; } @@ -327,7 +344,8 @@ static int fuse_readpage(struct file *file, struct page *page) req->out.page_zeroing = 1; req->num_pages = 1; req->pages[0] = page; - fuse_send_read(req, file, inode, page_offset(page), PAGE_CACHE_SIZE); + fuse_send_read(req, file, inode, page_offset(page), PAGE_CACHE_SIZE, + NULL); err = req->out.h.error; fuse_put_request(fc, req); if (!err) @@ -434,30 +452,47 @@ out: return err; } -static size_t fuse_send_write(struct fuse_req *req, struct file *file, - struct inode *inode, loff_t pos, size_t count) +static void fuse_write_fill(struct fuse_req *req, struct fuse_file *ff, + struct inode *inode, loff_t pos, size_t count, + int writepage) { struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_file *ff = file->private_data; - struct fuse_write_in inarg; - struct fuse_write_out outarg; + struct fuse_write_in *inarg = &req->misc.write.in; + struct fuse_write_out *outarg = &req->misc.write.out; - memset(&inarg, 0, sizeof(struct fuse_write_in)); - inarg.fh = ff->fh; - inarg.offset = pos; - inarg.size = count; + memset(inarg, 0, sizeof(struct fuse_write_in)); + inarg->fh = ff->fh; + inarg->offset = pos; + inarg->size = count; + inarg->write_flags = writepage ? FUSE_WRITE_CACHE : 0; req->in.h.opcode = FUSE_WRITE; req->in.h.nodeid = get_node_id(inode); req->in.argpages = 1; req->in.numargs = 2; - req->in.args[0].size = sizeof(struct fuse_write_in); - req->in.args[0].value = &inarg; + if (fc->minor < 9) + req->in.args[0].size = FUSE_COMPAT_WRITE_IN_SIZE; + else + req->in.args[0].size = sizeof(struct fuse_write_in); + req->in.args[0].value = inarg; req->in.args[1].size = count; req->out.numargs = 1; req->out.args[0].size = sizeof(struct fuse_write_out); - req->out.args[0].value = &outarg; + req->out.args[0].value = outarg; +} + +static size_t fuse_send_write(struct fuse_req *req, struct file *file, + struct inode *inode, loff_t pos, size_t count, + fl_owner_t owner) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + fuse_write_fill(req, file->private_data, inode, pos, count, 0); + if (owner != NULL) { + struct fuse_write_in *inarg = &req->misc.write.in; + inarg->write_flags |= FUSE_WRITE_LOCKOWNER; + inarg->lock_owner = fuse_lock_owner_id(fc, owner); + } request_send(fc, req); - return outarg.size; + return req->misc.write.out.size; } static int fuse_write_begin(struct file *file, struct address_space *mapping, @@ -478,6 +513,7 @@ static int fuse_buffered_write(struct file *file, struct inode *inode, int err; size_t nres; struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_inode *fi = get_fuse_inode(inode); unsigned offset = pos & (PAGE_CACHE_SIZE - 1); struct fuse_req *req; @@ -491,7 +527,7 @@ static int fuse_buffered_write(struct file *file, struct inode *inode, req->num_pages = 1; req->pages[0] = page; req->page_offset = offset; - nres = fuse_send_write(req, file, inode, pos, count); + nres = fuse_send_write(req, file, inode, pos, count, NULL); err = req->out.h.error; fuse_put_request(fc, req); if (!err && !nres) @@ -499,6 +535,7 @@ static int fuse_buffered_write(struct file *file, struct inode *inode, if (!err) { pos += nres; spin_lock(&fc->lock); + fi->attr_version = ++fc->attr_version; if (pos > inode->i_size) i_size_write(inode, pos); spin_unlock(&fc->lock); @@ -591,9 +628,11 @@ static ssize_t fuse_direct_io(struct file *file, const char __user *buf, nbytes = (req->num_pages << PAGE_SHIFT) - req->page_offset; nbytes = min(count, nbytes); if (write) - nres = fuse_send_write(req, file, inode, pos, nbytes); + nres = fuse_send_write(req, file, inode, pos, nbytes, + current->files); else - nres = fuse_send_read(req, file, inode, pos, nbytes); + nres = fuse_send_read(req, file, inode, pos, nbytes, + current->files); fuse_release_user_pages(req, !write); if (req->out.h.error) { if (!res) @@ -695,7 +734,8 @@ static int convert_fuse_file_lock(const struct fuse_file_lock *ffl, } static void fuse_lk_fill(struct fuse_req *req, struct file *file, - const struct file_lock *fl, int opcode, pid_t pid) + const struct file_lock *fl, int opcode, pid_t pid, + int flock) { struct inode *inode = file->f_path.dentry->d_inode; struct fuse_conn *fc = get_fuse_conn(inode); @@ -708,6 +748,8 @@ static void fuse_lk_fill(struct fuse_req *req, struct file *file, arg->lk.end = fl->fl_end; arg->lk.type = fl->fl_type; arg->lk.pid = pid; + if (flock) + arg->lk_flags |= FUSE_LK_FLOCK; req->in.h.opcode = opcode; req->in.h.nodeid = get_node_id(inode); req->in.numargs = 1; @@ -727,7 +769,7 @@ static int fuse_getlk(struct file *file, struct file_lock *fl) if (IS_ERR(req)) return PTR_ERR(req); - fuse_lk_fill(req, file, fl, FUSE_GETLK, 0); + fuse_lk_fill(req, file, fl, FUSE_GETLK, 0, 0); req->out.numargs = 1; req->out.args[0].size = sizeof(outarg); req->out.args[0].value = &outarg; @@ -740,7 +782,7 @@ static int fuse_getlk(struct file *file, struct file_lock *fl) return err; } -static int fuse_setlk(struct file *file, struct file_lock *fl) +static int fuse_setlk(struct file *file, struct file_lock *fl, int flock) { struct inode *inode = file->f_path.dentry->d_inode; struct fuse_conn *fc = get_fuse_conn(inode); @@ -757,7 +799,7 @@ static int fuse_setlk(struct file *file, struct file_lock *fl) if (IS_ERR(req)) return PTR_ERR(req); - fuse_lk_fill(req, file, fl, opcode, pid); + fuse_lk_fill(req, file, fl, opcode, pid, flock); request_send(fc, req); err = req->out.h.error; /* locking is restartable */ @@ -783,8 +825,25 @@ static int fuse_file_lock(struct file *file, int cmd, struct file_lock *fl) if (fc->no_lock) err = posix_lock_file_wait(file, fl); else - err = fuse_setlk(file, fl); + err = fuse_setlk(file, fl, 0); + } + return err; +} + +static int fuse_file_flock(struct file *file, int cmd, struct file_lock *fl) +{ + struct inode *inode = file->f_path.dentry->d_inode; + struct fuse_conn *fc = get_fuse_conn(inode); + int err; + + if (fc->no_lock) { + err = flock_lock_file_wait(file, fl); + } else { + /* emulate flock with POSIX locks */ + fl->fl_owner = (fl_owner_t) file; + err = fuse_setlk(file, fl, 1); } + return err; } @@ -836,6 +895,7 @@ static const struct file_operations fuse_file_operations = { .release = fuse_release, .fsync = fuse_fsync, .lock = fuse_file_lock, + .flock = fuse_file_flock, .splice_read = generic_file_splice_read, }; @@ -848,6 +908,7 @@ static const struct file_operations fuse_direct_io_file_operations = { .release = fuse_release, .fsync = fuse_fsync, .lock = fuse_file_lock, + .flock = fuse_file_flock, /* no mmap and splice_read */ }; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 1764506..6c5461d 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -67,6 +67,12 @@ struct fuse_inode { /** The sticky bit in inode->i_mode may have been removed, so preserve the original mode */ mode_t orig_i_mode; + + /** Version of last attribute change */ + u64 attr_version; + + /** Files usable in writepage. Protected by fc->lock */ + struct list_head write_files; }; /** FUSE specific file data */ @@ -79,6 +85,9 @@ struct fuse_file { /** Refcount */ atomic_t count; + + /** Entry on inode's write_files list */ + struct list_head write_entry; }; /** One input argument of a request */ @@ -210,6 +219,10 @@ struct fuse_req { struct fuse_init_in init_in; struct fuse_init_out init_out; struct fuse_read_in read_in; + struct { + struct fuse_write_in in; + struct fuse_write_out out; + } write; struct fuse_lk_in lk_in; } misc; @@ -317,6 +330,9 @@ struct fuse_conn { /** Do readpages asynchronously? Only set in INIT */ unsigned async_read : 1; + /** Do not send separate SETATTR request before open(O_TRUNC) */ + unsigned atomic_o_trunc : 1; + /* * The following bitfields are only for optimization purposes * and hence races in setting them will not cause malfunction @@ -387,6 +403,9 @@ struct fuse_conn { /** Reserved request for the DESTROY message */ struct fuse_req *destroy_req; + + /** Version counter for attribute changes */ + u64 attr_version; }; static inline struct fuse_conn *get_fuse_conn_super(struct super_block *sb) @@ -416,7 +435,8 @@ extern const struct file_operations fuse_dev_operations; * Get a filled in inode */ struct inode *fuse_iget(struct super_block *sb, unsigned long nodeid, - int generation, struct fuse_attr *attr); + int generation, struct fuse_attr *attr, + u64 attr_valid, u64 attr_version); /** * Send FORGET command @@ -477,7 +497,8 @@ void fuse_init_symlink(struct inode *inode); /** * Change attributes of an inode */ -void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr); +void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, + u64 attr_valid, u64 attr_version); /** * Initialize the client device @@ -565,3 +586,10 @@ void fuse_ctl_remove_conn(struct fuse_conn *fc); * Is file type valid? */ int fuse_valid_type(int m); + +/** + * Is task allowed to perform filesystem operation? + */ +int fuse_allow_task(struct fuse_conn *fc, struct task_struct *task); + +u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index fd07357..9a68d69 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -56,6 +56,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb) fi->i_time = 0; fi->nodeid = 0; fi->nlookup = 0; + INIT_LIST_HEAD(&fi->write_files); fi->forget_req = fuse_request_alloc(); if (!fi->forget_req) { kmem_cache_free(fuse_inode_cachep, inode); @@ -68,6 +69,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb) static void fuse_destroy_inode(struct inode *inode) { struct fuse_inode *fi = get_fuse_inode(inode); + BUG_ON(!list_empty(&fi->write_files)); if (fi->forget_req) fuse_request_free(fi->forget_req); kmem_cache_free(fuse_inode_cachep, inode); @@ -117,12 +119,22 @@ static void fuse_truncate(struct address_space *mapping, loff_t offset) unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1); } -void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr) + +void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, + u64 attr_valid, u64 attr_version) { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); loff_t oldsize; + spin_lock(&fc->lock); + if (attr_version != 0 && fi->attr_version > attr_version) { + spin_unlock(&fc->lock); + return; + } + fi->attr_version = ++fc->attr_version; + fi->i_time = attr_valid; + inode->i_ino = attr->ino; inode->i_mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777); inode->i_nlink = attr->nlink; @@ -136,6 +148,11 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr) inode->i_ctime.tv_sec = attr->ctime; inode->i_ctime.tv_nsec = attr->ctimensec; + if (attr->blksize != 0) + inode->i_blkbits = ilog2(attr->blksize); + else + inode->i_blkbits = inode->i_sb->s_blocksize_bits; + /* * Don't set the sticky bit in i_mode, unless we want the VFS * to check permissions. This prevents failures due to the @@ -145,7 +162,6 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr) if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS)) inode->i_mode &= ~S_ISVTX; - spin_lock(&fc->lock); oldsize = inode->i_size; i_size_write(inode, attr->size); spin_unlock(&fc->lock); @@ -194,7 +210,8 @@ static int fuse_inode_set(struct inode *inode, void *_nodeidp) } struct inode *fuse_iget(struct super_block *sb, unsigned long nodeid, - int generation, struct fuse_attr *attr) + int generation, struct fuse_attr *attr, + u64 attr_valid, u64 attr_version) { struct inode *inode; struct fuse_inode *fi; @@ -222,7 +239,8 @@ struct inode *fuse_iget(struct super_block *sb, unsigned long nodeid, spin_lock(&fc->lock); fi->nlookup ++; spin_unlock(&fc->lock); - fuse_change_attributes(inode, attr); + fuse_change_attributes(inode, attr, attr_valid, attr_version); + return inode; } @@ -287,6 +305,11 @@ static int fuse_statfs(struct dentry *dentry, struct kstatfs *buf) struct fuse_statfs_out outarg; int err; + if (!fuse_allow_task(fc, current)) { + buf->f_type = FUSE_SUPER_MAGIC; + return 0; + } + req = fuse_get_req(fc); if (IS_ERR(req)) return PTR_ERR(req); @@ -452,6 +475,7 @@ static struct fuse_conn *new_conn(void) } fc->reqctr = 0; fc->blocked = 1; + fc->attr_version = 1; get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key)); } out: @@ -483,7 +507,7 @@ static struct inode *get_root_inode(struct super_block *sb, unsigned mode) attr.mode = mode; attr.ino = FUSE_ROOT_ID; attr.nlink = 1; - return fuse_iget(sb, 1, 0, &attr); + return fuse_iget(sb, 1, 0, &attr, 0, 0); } static const struct super_operations fuse_super_operations = { @@ -514,6 +538,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fc->async_read = 1; if (!(arg->flags & FUSE_POSIX_LOCKS)) fc->no_lock = 1; + if (arg->flags & FUSE_ATOMIC_O_TRUNC) + fc->atomic_o_trunc = 1; } else { ra_pages = fc->max_read / PAGE_CACHE_SIZE; fc->no_lock = 1; @@ -536,7 +562,8 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) arg->major = FUSE_KERNEL_VERSION; arg->minor = FUSE_KERNEL_MINOR_VERSION; arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE; - arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS; + arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_FILE_OPS | + FUSE_ATOMIC_O_TRUNC; req->in.h.opcode = FUSE_INIT; req->in.numargs = 1; req->in.args[0].size = sizeof(*arg); diff --git a/fs/ioprio.c b/fs/ioprio.c index 10d2c21..d6ff77e 100644 --- a/fs/ioprio.c +++ b/fs/ioprio.c @@ -25,6 +25,7 @@ #include <linux/capability.h> #include <linux/syscalls.h> #include <linux/security.h> +#include <linux/pid_namespace.h> static int set_task_ioprio(struct task_struct *task, int ioprio) { @@ -93,7 +94,7 @@ asmlinkage long sys_ioprio_set(int which, int who, int ioprio) if (!who) p = current; else - p = find_task_by_pid(who); + p = find_task_by_vpid(who); if (p) ret = set_task_ioprio(p, ioprio); break; @@ -101,7 +102,7 @@ asmlinkage long sys_ioprio_set(int which, int who, int ioprio) if (!who) pgrp = task_pgrp(current); else - pgrp = find_pid(who); + pgrp = find_vpid(who); do_each_pid_task(pgrp, PIDTYPE_PGID, p) { ret = set_task_ioprio(p, ioprio); if (ret) @@ -180,7 +181,7 @@ asmlinkage long sys_ioprio_get(int which, int who) if (!who) p = current; else - p = find_task_by_pid(who); + p = find_task_by_vpid(who); if (p) ret = get_task_ioprio(p); break; @@ -188,7 +189,7 @@ asmlinkage long sys_ioprio_get(int which, int who) if (!who) pgrp = task_pgrp(current); else - pgrp = find_pid(who); + pgrp = find_vpid(who); do_each_pid_task(pgrp, PIDTYPE_PGID, p) { tmpio = get_task_ioprio(p); if (tmpio < 0) diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index a003d50..8f1f2aa 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -375,7 +375,7 @@ void journal_commit_transaction(journal_t *journal) struct buffer_head *bh = jh2bh(jh); jbd_lock_bh_state(bh); - jbd_slab_free(jh->b_committed_data, bh->b_size); + jbd_free(jh->b_committed_data, bh->b_size); jh->b_committed_data = NULL; jbd_unlock_bh_state(bh); } @@ -466,7 +466,7 @@ void journal_commit_transaction(journal_t *journal) spin_unlock(&journal->j_list_lock); if (err) - __journal_abort_hard(journal); + journal_abort(journal, err); journal_write_revoke_records(journal, commit_transaction); @@ -524,7 +524,7 @@ void journal_commit_transaction(journal_t *journal) descriptor = journal_get_descriptor_buffer(journal); if (!descriptor) { - __journal_abort_hard(journal); + journal_abort(journal, -EIO); continue; } @@ -557,7 +557,7 @@ void journal_commit_transaction(journal_t *journal) and repeat this loop: we'll fall into the refile-on-abort condition above. */ if (err) { - __journal_abort_hard(journal); + journal_abort(journal, err); continue; } @@ -748,7 +748,7 @@ wait_for_iobuf: err = -EIO; if (err) - __journal_abort_hard(journal); + journal_abort(journal, err); /* End of a transaction! Finally, we can do checkpoint processing: any buffers committed as a result of this @@ -792,14 +792,14 @@ restart_loop: * Otherwise, we can just throw away the frozen data now. */ if (jh->b_committed_data) { - jbd_slab_free(jh->b_committed_data, bh->b_size); + jbd_free(jh->b_committed_data, bh->b_size); jh->b_committed_data = NULL; if (jh->b_frozen_data) { jh->b_committed_data = jh->b_frozen_data; jh->b_frozen_data = NULL; } } else if (jh->b_frozen_data) { - jbd_slab_free(jh->b_frozen_data, bh->b_size); + jbd_free(jh->b_frozen_data, bh->b_size); jh->b_frozen_data = NULL; } diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index a6be78c..5d14243 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -35,6 +35,7 @@ #include <linux/kthread.h> #include <linux/poison.h> #include <linux/proc_fs.h> +#include <linux/debugfs.h> #include <asm/uaccess.h> #include <asm/page.h> @@ -83,7 +84,6 @@ EXPORT_SYMBOL(journal_force_commit); static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *); static void __journal_abort_soft (journal_t *journal, int errno); -static int journal_create_jbd_slab(size_t slab_size); /* * Helper function used to manage commit timeouts @@ -218,7 +218,7 @@ static int journal_start_thread(journal_t *journal) if (IS_ERR(t)) return PTR_ERR(t); - wait_event(journal->j_wait_done_commit, journal->j_task != 0); + wait_event(journal->j_wait_done_commit, journal->j_task != NULL); return 0; } @@ -230,7 +230,8 @@ static void journal_kill_thread(journal_t *journal) while (journal->j_task) { wake_up(&journal->j_wait_commit); spin_unlock(&journal->j_state_lock); - wait_event(journal->j_wait_done_commit, journal->j_task == 0); + wait_event(journal->j_wait_done_commit, + journal->j_task == NULL); spin_lock(&journal->j_state_lock); } spin_unlock(&journal->j_state_lock); @@ -334,10 +335,10 @@ repeat: char *tmp; jbd_unlock_bh_state(bh_in); - tmp = jbd_slab_alloc(bh_in->b_size, GFP_NOFS); + tmp = jbd_alloc(bh_in->b_size, GFP_NOFS); jbd_lock_bh_state(bh_in); if (jh_in->b_frozen_data) { - jbd_slab_free(tmp, bh_in->b_size); + jbd_free(tmp, bh_in->b_size); goto repeat; } @@ -654,10 +655,9 @@ static journal_t * journal_init_common (void) journal_t *journal; int err; - journal = jbd_kmalloc(sizeof(*journal), GFP_KERNEL); + journal = kzalloc(sizeof(*journal), GFP_KERNEL); if (!journal) goto fail; - memset(journal, 0, sizeof(*journal)); init_waitqueue_head(&journal->j_wait_transaction_locked); init_waitqueue_head(&journal->j_wait_logspace); @@ -1095,13 +1095,6 @@ int journal_load(journal_t *journal) } } - /* - * Create a slab for this blocksize - */ - err = journal_create_jbd_slab(be32_to_cpu(sb->s_blocksize)); - if (err) - return err; - /* Let the recovery code check whether it needs to recover any * data from the journal. */ if (journal_recover(journal)) @@ -1615,86 +1608,6 @@ int journal_blocks_per_page(struct inode *inode) } /* - * Simple support for retrying memory allocations. Introduced to help to - * debug different VM deadlock avoidance strategies. - */ -void * __jbd_kmalloc (const char *where, size_t size, gfp_t flags, int retry) -{ - return kmalloc(size, flags | (retry ? __GFP_NOFAIL : 0)); -} - -/* - * jbd slab management: create 1k, 2k, 4k, 8k slabs as needed - * and allocate frozen and commit buffers from these slabs. - * - * Reason for doing this is to avoid, SLAB_DEBUG - since it could - * cause bh to cross page boundary. - */ - -#define JBD_MAX_SLABS 5 -#define JBD_SLAB_INDEX(size) (size >> 11) - -static struct kmem_cache *jbd_slab[JBD_MAX_SLABS]; -static const char *jbd_slab_names[JBD_MAX_SLABS] = { - "jbd_1k", "jbd_2k", "jbd_4k", NULL, "jbd_8k" -}; - -static void journal_destroy_jbd_slabs(void) -{ - int i; - - for (i = 0; i < JBD_MAX_SLABS; i++) { - if (jbd_slab[i]) - kmem_cache_destroy(jbd_slab[i]); - jbd_slab[i] = NULL; - } -} - -static int journal_create_jbd_slab(size_t slab_size) -{ - int i = JBD_SLAB_INDEX(slab_size); - - BUG_ON(i >= JBD_MAX_SLABS); - - /* - * Check if we already have a slab created for this size - */ - if (jbd_slab[i]) - return 0; - - /* - * Create a slab and force alignment to be same as slabsize - - * this will make sure that allocations won't cross the page - * boundary. - */ - jbd_slab[i] = kmem_cache_create(jbd_slab_names[i], - slab_size, slab_size, 0, NULL); - if (!jbd_slab[i]) { - printk(KERN_EMERG "JBD: no memory for jbd_slab cache\n"); - return -ENOMEM; - } - return 0; -} - -void * jbd_slab_alloc(size_t size, gfp_t flags) -{ - int idx; - - idx = JBD_SLAB_INDEX(size); - BUG_ON(jbd_slab[idx] == NULL); - return kmem_cache_alloc(jbd_slab[idx], flags | __GFP_NOFAIL); -} - -void jbd_slab_free(void *ptr, size_t size) -{ - int idx; - - idx = JBD_SLAB_INDEX(size); - BUG_ON(jbd_slab[idx] == NULL); - kmem_cache_free(jbd_slab[idx], ptr); -} - -/* * Journal_head storage management */ static struct kmem_cache *journal_head_cache; @@ -1739,14 +1652,14 @@ static struct journal_head *journal_alloc_journal_head(void) atomic_inc(&nr_journal_heads); #endif ret = kmem_cache_alloc(journal_head_cache, GFP_NOFS); - if (ret == 0) { + if (ret == NULL) { jbd_debug(1, "out of memory for journal_head\n"); if (time_after(jiffies, last_warning + 5*HZ)) { printk(KERN_NOTICE "ENOMEM in %s, retrying.\n", __FUNCTION__); last_warning = jiffies; } - while (ret == 0) { + while (ret == NULL) { yield(); ret = kmem_cache_alloc(journal_head_cache, GFP_NOFS); } @@ -1881,13 +1794,13 @@ static void __journal_remove_journal_head(struct buffer_head *bh) printk(KERN_WARNING "%s: freeing " "b_frozen_data\n", __FUNCTION__); - jbd_slab_free(jh->b_frozen_data, bh->b_size); + jbd_free(jh->b_frozen_data, bh->b_size); } if (jh->b_committed_data) { printk(KERN_WARNING "%s: freeing " "b_committed_data\n", __FUNCTION__); - jbd_slab_free(jh->b_committed_data, bh->b_size); + jbd_free(jh->b_committed_data, bh->b_size); } bh->b_private = NULL; jh->b_bh = NULL; /* debug, really */ @@ -1939,64 +1852,41 @@ void journal_put_journal_head(struct journal_head *jh) } /* - * /proc tunables + * debugfs tunables */ -#if defined(CONFIG_JBD_DEBUG) -int journal_enable_debug; -EXPORT_SYMBOL(journal_enable_debug); -#endif +#ifdef CONFIG_JBD_DEBUG -#if defined(CONFIG_JBD_DEBUG) && defined(CONFIG_PROC_FS) +u8 journal_enable_debug __read_mostly; +EXPORT_SYMBOL(journal_enable_debug); -static struct proc_dir_entry *proc_jbd_debug; +static struct dentry *jbd_debugfs_dir; +static struct dentry *jbd_debug; -static int read_jbd_debug(char *page, char **start, off_t off, - int count, int *eof, void *data) +static void __init jbd_create_debugfs_entry(void) { - int ret; - - ret = sprintf(page + off, "%d\n", journal_enable_debug); - *eof = 1; - return ret; + jbd_debugfs_dir = debugfs_create_dir("jbd", NULL); + if (jbd_debugfs_dir) + jbd_debug = debugfs_create_u8("jbd-debug", S_IRUGO, + jbd_debugfs_dir, + &journal_enable_debug); } -static int write_jbd_debug(struct file *file, const char __user *buffer, - unsigned long count, void *data) +static void __exit jbd_remove_debugfs_entry(void) { - char buf[32]; - - if (count > ARRAY_SIZE(buf) - 1) - count = ARRAY_SIZE(buf) - 1; - if (copy_from_user(buf, buffer, count)) - return -EFAULT; - buf[ARRAY_SIZE(buf) - 1] = '\0'; - journal_enable_debug = simple_strtoul(buf, NULL, 10); - return count; + debugfs_remove(jbd_debug); + debugfs_remove(jbd_debugfs_dir); } -#define JBD_PROC_NAME "sys/fs/jbd-debug" +#else -static void __init create_jbd_proc_entry(void) +static inline void jbd_create_debugfs_entry(void) { - proc_jbd_debug = create_proc_entry(JBD_PROC_NAME, 0644, NULL); - if (proc_jbd_debug) { - /* Why is this so hard? */ - proc_jbd_debug->read_proc = read_jbd_debug; - proc_jbd_debug->write_proc = write_jbd_debug; - } } -static void __exit remove_jbd_proc_entry(void) +static inline void jbd_remove_debugfs_entry(void) { - if (proc_jbd_debug) - remove_proc_entry(JBD_PROC_NAME, NULL); } -#else - -#define create_jbd_proc_entry() do {} while (0) -#define remove_jbd_proc_entry() do {} while (0) - #endif struct kmem_cache *jbd_handle_cache; @@ -2042,7 +1932,6 @@ static void journal_destroy_caches(void) journal_destroy_revoke_caches(); journal_destroy_journal_head_cache(); journal_destroy_handle_cache(); - journal_destroy_jbd_slabs(); } static int __init journal_init(void) @@ -2054,7 +1943,7 @@ static int __init journal_init(void) ret = journal_init_caches(); if (ret != 0) journal_destroy_caches(); - create_jbd_proc_entry(); + jbd_create_debugfs_entry(); return ret; } @@ -2065,7 +1954,7 @@ static void __exit journal_exit(void) if (n) printk(KERN_EMERG "JBD: leaked %d journal_heads!\n", n); #endif - remove_jbd_proc_entry(); + jbd_remove_debugfs_entry(); journal_destroy_caches(); } diff --git a/fs/jbd/recovery.c b/fs/jbd/recovery.c index 2a5f4b8..c5d9694 100644 --- a/fs/jbd/recovery.c +++ b/fs/jbd/recovery.c @@ -250,10 +250,10 @@ int journal_recover(journal_t *journal) if (!err) err = do_one_pass(journal, &info, PASS_REPLAY); - jbd_debug(0, "JBD: recovery, exit status %d, " + jbd_debug(1, "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(1, "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 @@ -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(1, "JBD: ignoring %d transaction%s from the journal.\n", dropped, (dropped == 1) ? "" : "s"); journal->j_transaction_sequence = ++info.end_transaction; diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index 8df5bac..08ff6c7 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -96,13 +96,12 @@ static int start_this_handle(journal_t *journal, handle_t *handle) alloc_transaction: if (!journal->j_running_transaction) { - new_transaction = jbd_kmalloc(sizeof(*new_transaction), - GFP_NOFS); + new_transaction = kzalloc(sizeof(*new_transaction), + GFP_NOFS|__GFP_NOFAIL); if (!new_transaction) { ret = -ENOMEM; goto out; } - memset(new_transaction, 0, sizeof(*new_transaction)); } jbd_debug(3, "New handle %p going live.\n", handle); @@ -675,7 +674,7 @@ repeat: JBUFFER_TRACE(jh, "allocate memory for buffer"); jbd_unlock_bh_state(bh); frozen_buffer = - jbd_slab_alloc(jh2bh(jh)->b_size, + jbd_alloc(jh2bh(jh)->b_size, GFP_NOFS); if (!frozen_buffer) { printk(KERN_EMERG @@ -735,7 +734,7 @@ done: out: if (unlikely(frozen_buffer)) /* It's usually NULL */ - jbd_slab_free(frozen_buffer, bh->b_size); + jbd_free(frozen_buffer, bh->b_size); JBUFFER_TRACE(jh, "exit"); return error; @@ -888,7 +887,7 @@ int journal_get_undo_access(handle_t *handle, struct buffer_head *bh) repeat: if (!jh->b_committed_data) { - committed_data = jbd_slab_alloc(jh2bh(jh)->b_size, GFP_NOFS); + committed_data = jbd_alloc(jh2bh(jh)->b_size, GFP_NOFS); if (!committed_data) { printk(KERN_EMERG "%s: No memory for committed data\n", __FUNCTION__); @@ -915,7 +914,7 @@ repeat: out: journal_put_journal_head(jh); if (unlikely(committed_data)) - jbd_slab_free(committed_data, bh->b_size); + jbd_free(committed_data, bh->b_size); return err; } @@ -1172,7 +1171,7 @@ int journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) } /* That test should have eliminated the following case: */ - J_ASSERT_JH(jh, jh->b_frozen_data == 0); + J_ASSERT_JH(jh, jh->b_frozen_data == NULL); JBUFFER_TRACE(jh, "file as BJ_Metadata"); spin_lock(&journal->j_list_lock); @@ -1522,7 +1521,7 @@ static void __journal_temp_unlink_buffer(struct journal_head *jh) J_ASSERT_JH(jh, jh->b_jlist < BJ_Types); if (jh->b_jlist != BJ_None) - J_ASSERT_JH(jh, transaction != 0); + J_ASSERT_JH(jh, transaction != NULL); switch (jh->b_jlist) { case BJ_None: @@ -1591,11 +1590,11 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh) if (buffer_locked(bh) || buffer_dirty(bh)) goto out; - if (jh->b_next_transaction != 0) + if (jh->b_next_transaction != NULL) goto out; spin_lock(&journal->j_list_lock); - if (jh->b_transaction != 0 && jh->b_cp_transaction == 0) { + if (jh->b_transaction != NULL && jh->b_cp_transaction == NULL) { if (jh->b_jlist == BJ_SyncData || jh->b_jlist == BJ_Locked) { /* A written-back ordered data buffer */ JBUFFER_TRACE(jh, "release data"); @@ -1603,7 +1602,7 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh) journal_remove_journal_head(bh); __brelse(bh); } - } else if (jh->b_cp_transaction != 0 && jh->b_transaction == 0) { + } else if (jh->b_cp_transaction != NULL && jh->b_transaction == NULL) { /* written-back checkpointed metadata buffer */ if (jh->b_jlist == BJ_None) { JBUFFER_TRACE(jh, "remove from checkpoint list"); @@ -1963,7 +1962,7 @@ void __journal_file_buffer(struct journal_head *jh, J_ASSERT_JH(jh, jh->b_jlist < BJ_Types); J_ASSERT_JH(jh, jh->b_transaction == transaction || - jh->b_transaction == 0); + jh->b_transaction == NULL); if (jh->b_transaction && jh->b_jlist == jlist) return; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index c0f59d1..6986f33 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -278,7 +278,7 @@ static inline void write_tag_block(int tag_bytes, journal_block_tag_t *tag, unsigned long long block) { tag->t_blocknr = cpu_to_be32(block & (u32)~0); - if (tag_bytes > JBD_TAG_SIZE32) + if (tag_bytes > JBD2_TAG_SIZE32) tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1); } @@ -384,7 +384,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) struct buffer_head *bh = jh2bh(jh); jbd_lock_bh_state(bh); - jbd2_slab_free(jh->b_committed_data, bh->b_size); + jbd2_free(jh->b_committed_data, bh->b_size); jh->b_committed_data = NULL; jbd_unlock_bh_state(bh); } @@ -475,7 +475,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) spin_unlock(&journal->j_list_lock); if (err) - __jbd2_journal_abort_hard(journal); + jbd2_journal_abort(journal, err); jbd2_journal_write_revoke_records(journal, commit_transaction); @@ -533,7 +533,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) descriptor = jbd2_journal_get_descriptor_buffer(journal); if (!descriptor) { - __jbd2_journal_abort_hard(journal); + jbd2_journal_abort(journal, -EIO); continue; } @@ -566,7 +566,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) and repeat this loop: we'll fall into the refile-on-abort condition above. */ if (err) { - __jbd2_journal_abort_hard(journal); + jbd2_journal_abort(journal, err); continue; } @@ -757,7 +757,7 @@ wait_for_iobuf: err = -EIO; if (err) - __jbd2_journal_abort_hard(journal); + jbd2_journal_abort(journal, err); /* End of a transaction! Finally, we can do checkpoint processing: any buffers committed as a result of this @@ -801,14 +801,14 @@ restart_loop: * Otherwise, we can just throw away the frozen data now. */ if (jh->b_committed_data) { - jbd2_slab_free(jh->b_committed_data, bh->b_size); + jbd2_free(jh->b_committed_data, bh->b_size); jh->b_committed_data = NULL; if (jh->b_frozen_data) { jh->b_committed_data = jh->b_frozen_data; jh->b_frozen_data = NULL; } } else if (jh->b_frozen_data) { - jbd2_slab_free(jh->b_frozen_data, bh->b_size); + jbd2_free(jh->b_frozen_data, bh->b_size); jh->b_frozen_data = NULL; } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index f37324a..6ddc553 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -84,7 +84,6 @@ EXPORT_SYMBOL(jbd2_journal_force_commit); static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *); static void __journal_abort_soft (journal_t *journal, int errno); -static int jbd2_journal_create_jbd_slab(size_t slab_size); /* * Helper function used to manage commit timeouts @@ -335,10 +334,10 @@ repeat: char *tmp; jbd_unlock_bh_state(bh_in); - tmp = jbd2_slab_alloc(bh_in->b_size, GFP_NOFS); + tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS); jbd_lock_bh_state(bh_in); if (jh_in->b_frozen_data) { - jbd2_slab_free(tmp, bh_in->b_size); + jbd2_free(tmp, bh_in->b_size); goto repeat; } @@ -655,10 +654,9 @@ static journal_t * journal_init_common (void) journal_t *journal; int err; - journal = jbd_kmalloc(sizeof(*journal), GFP_KERNEL); + journal = kzalloc(sizeof(*journal), GFP_KERNEL|__GFP_NOFAIL); if (!journal) goto fail; - memset(journal, 0, sizeof(*journal)); init_waitqueue_head(&journal->j_wait_transaction_locked); init_waitqueue_head(&journal->j_wait_logspace); @@ -672,7 +670,7 @@ static journal_t * journal_init_common (void) spin_lock_init(&journal->j_list_lock); spin_lock_init(&journal->j_state_lock); - journal->j_commit_interval = (HZ * JBD_DEFAULT_MAX_COMMIT_AGE); + journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE); /* The journal is marked for error until we succeed with recovery! */ journal->j_flags = JBD2_ABORT; @@ -1096,13 +1094,6 @@ int jbd2_journal_load(journal_t *journal) } } - /* - * Create a slab for this blocksize - */ - err = jbd2_journal_create_jbd_slab(be32_to_cpu(sb->s_blocksize)); - if (err) - return err; - /* Let the recovery code check whether it needs to recover any * data from the journal. */ if (jbd2_journal_recover(journal)) @@ -1621,89 +1612,9 @@ int jbd2_journal_blocks_per_page(struct inode *inode) size_t journal_tag_bytes(journal_t *journal) { if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) - return JBD_TAG_SIZE64; + return JBD2_TAG_SIZE64; else - return JBD_TAG_SIZE32; -} - -/* - * Simple support for retrying memory allocations. Introduced to help to - * debug different VM deadlock avoidance strategies. - */ -void * __jbd2_kmalloc (const char *where, size_t size, gfp_t flags, int retry) -{ - return kmalloc(size, flags | (retry ? __GFP_NOFAIL : 0)); -} - -/* - * jbd slab management: create 1k, 2k, 4k, 8k slabs as needed - * and allocate frozen and commit buffers from these slabs. - * - * Reason for doing this is to avoid, SLAB_DEBUG - since it could - * cause bh to cross page boundary. - */ - -#define JBD_MAX_SLABS 5 -#define JBD_SLAB_INDEX(size) (size >> 11) - -static struct kmem_cache *jbd_slab[JBD_MAX_SLABS]; -static const char *jbd_slab_names[JBD_MAX_SLABS] = { - "jbd2_1k", "jbd2_2k", "jbd2_4k", NULL, "jbd2_8k" -}; - -static void jbd2_journal_destroy_jbd_slabs(void) -{ - int i; - - for (i = 0; i < JBD_MAX_SLABS; i++) { - if (jbd_slab[i]) - kmem_cache_destroy(jbd_slab[i]); - jbd_slab[i] = NULL; - } -} - -static int jbd2_journal_create_jbd_slab(size_t slab_size) -{ - int i = JBD_SLAB_INDEX(slab_size); - - BUG_ON(i >= JBD_MAX_SLABS); - - /* - * Check if we already have a slab created for this size - */ - if (jbd_slab[i]) - return 0; - - /* - * Create a slab and force alignment to be same as slabsize - - * this will make sure that allocations won't cross the page - * boundary. - */ - jbd_slab[i] = kmem_cache_create(jbd_slab_names[i], - slab_size, slab_size, 0, NULL); - if (!jbd_slab[i]) { - printk(KERN_EMERG "JBD: no memory for jbd_slab cache\n"); - return -ENOMEM; - } - return 0; -} - -void * jbd2_slab_alloc(size_t size, gfp_t flags) -{ - int idx; - - idx = JBD_SLAB_INDEX(size); - BUG_ON(jbd_slab[idx] == NULL); - return kmem_cache_alloc(jbd_slab[idx], flags | __GFP_NOFAIL); -} - -void jbd2_slab_free(void *ptr, size_t size) -{ - int idx; - - idx = JBD_SLAB_INDEX(size); - BUG_ON(jbd_slab[idx] == NULL); - kmem_cache_free(jbd_slab[idx], ptr); + return JBD2_TAG_SIZE32; } /* @@ -1770,7 +1681,7 @@ static void journal_free_journal_head(struct journal_head *jh) { #ifdef CONFIG_JBD2_DEBUG atomic_dec(&nr_journal_heads); - memset(jh, JBD_POISON_FREE, sizeof(*jh)); + memset(jh, JBD2_POISON_FREE, sizeof(*jh)); #endif kmem_cache_free(jbd2_journal_head_cache, jh); } @@ -1893,13 +1804,13 @@ static void __journal_remove_journal_head(struct buffer_head *bh) printk(KERN_WARNING "%s: freeing " "b_frozen_data\n", __FUNCTION__); - jbd2_slab_free(jh->b_frozen_data, bh->b_size); + jbd2_free(jh->b_frozen_data, bh->b_size); } if (jh->b_committed_data) { printk(KERN_WARNING "%s: freeing " "b_committed_data\n", __FUNCTION__); - jbd2_slab_free(jh->b_committed_data, bh->b_size); + jbd2_free(jh->b_committed_data, bh->b_size); } bh->b_private = NULL; jh->b_bh = NULL; /* debug, really */ @@ -1953,16 +1864,14 @@ void jbd2_journal_put_journal_head(struct journal_head *jh) /* * debugfs tunables */ -#if defined(CONFIG_JBD2_DEBUG) -u8 jbd2_journal_enable_debug; +#ifdef CONFIG_JBD2_DEBUG +u8 jbd2_journal_enable_debug __read_mostly; EXPORT_SYMBOL(jbd2_journal_enable_debug); -#endif - -#if defined(CONFIG_JBD2_DEBUG) && defined(CONFIG_DEBUG_FS) #define JBD2_DEBUG_NAME "jbd2-debug" -struct dentry *jbd2_debugfs_dir, *jbd2_debug; +static struct dentry *jbd2_debugfs_dir; +static struct dentry *jbd2_debug; static void __init jbd2_create_debugfs_entry(void) { @@ -1975,24 +1884,18 @@ static void __init jbd2_create_debugfs_entry(void) static void __exit jbd2_remove_debugfs_entry(void) { - if (jbd2_debug) - debugfs_remove(jbd2_debug); - if (jbd2_debugfs_dir) - debugfs_remove(jbd2_debugfs_dir); + debugfs_remove(jbd2_debug); + debugfs_remove(jbd2_debugfs_dir); } #else static void __init jbd2_create_debugfs_entry(void) { - do { - } while (0); } static void __exit jbd2_remove_debugfs_entry(void) { - do { - } while (0); } #endif @@ -2040,7 +1943,6 @@ static void jbd2_journal_destroy_caches(void) jbd2_journal_destroy_revoke_caches(); jbd2_journal_destroy_jbd2_journal_head_cache(); jbd2_journal_destroy_handle_cache(); - jbd2_journal_destroy_jbd_slabs(); } static int __init journal_init(void) diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index b50be8a..d0ce627 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -311,7 +311,7 @@ int jbd2_journal_skip_recovery(journal_t *journal) static inline unsigned long long read_tag_block(int tag_bytes, journal_block_tag_t *tag) { unsigned long long block = be32_to_cpu(tag->t_blocknr); - if (tag_bytes > JBD_TAG_SIZE32) + if (tag_bytes > JBD2_TAG_SIZE32) block |= (u64)be32_to_cpu(tag->t_blocknr_high) << 32; return block; } diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index 01d8897..3595fd4 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -352,7 +352,7 @@ int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr, if (bh) BUFFER_TRACE(bh, "found on hash"); } -#ifdef JBD_EXPENSIVE_CHECKING +#ifdef JBD2_EXPENSIVE_CHECKING else { struct buffer_head *bh2; @@ -453,7 +453,7 @@ int jbd2_journal_cancel_revoke(handle_t *handle, struct journal_head *jh) } } -#ifdef JBD_EXPENSIVE_CHECKING +#ifdef JBD2_EXPENSIVE_CHECKING /* There better not be one left behind by now! */ record = find_revoke_record(journal, bh->b_blocknr); J_ASSERT_JH(jh, record == NULL); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 7946ff4..b1fcf2b 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -96,13 +96,12 @@ static int start_this_handle(journal_t *journal, handle_t *handle) alloc_transaction: if (!journal->j_running_transaction) { - new_transaction = jbd_kmalloc(sizeof(*new_transaction), - GFP_NOFS); + new_transaction = kzalloc(sizeof(*new_transaction), + GFP_NOFS|__GFP_NOFAIL); if (!new_transaction) { ret = -ENOMEM; goto out; } - memset(new_transaction, 0, sizeof(*new_transaction)); } jbd_debug(3, "New handle %p going live.\n", handle); @@ -236,7 +235,7 @@ out: /* Allocate a new handle. This should probably be in a slab... */ static handle_t *new_handle(int nblocks) { - handle_t *handle = jbd_alloc_handle(GFP_NOFS); + handle_t *handle = jbd2_alloc_handle(GFP_NOFS); if (!handle) return NULL; memset(handle, 0, sizeof(*handle)); @@ -282,7 +281,7 @@ handle_t *jbd2_journal_start(journal_t *journal, int nblocks) err = start_this_handle(journal, handle); if (err < 0) { - jbd_free_handle(handle); + jbd2_free_handle(handle); current->journal_info = NULL; handle = ERR_PTR(err); } @@ -668,7 +667,7 @@ repeat: JBUFFER_TRACE(jh, "allocate memory for buffer"); jbd_unlock_bh_state(bh); frozen_buffer = - jbd2_slab_alloc(jh2bh(jh)->b_size, + jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS); if (!frozen_buffer) { printk(KERN_EMERG @@ -728,7 +727,7 @@ done: out: if (unlikely(frozen_buffer)) /* It's usually NULL */ - jbd2_slab_free(frozen_buffer, bh->b_size); + jbd2_free(frozen_buffer, bh->b_size); JBUFFER_TRACE(jh, "exit"); return error; @@ -881,7 +880,7 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh) repeat: if (!jh->b_committed_data) { - committed_data = jbd2_slab_alloc(jh2bh(jh)->b_size, GFP_NOFS); + committed_data = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS); if (!committed_data) { printk(KERN_EMERG "%s: No memory for committed data\n", __FUNCTION__); @@ -908,7 +907,7 @@ repeat: out: jbd2_journal_put_journal_head(jh); if (unlikely(committed_data)) - jbd2_slab_free(committed_data, bh->b_size); + jbd2_free(committed_data, bh->b_size); return err; } @@ -1411,7 +1410,7 @@ int jbd2_journal_stop(handle_t *handle) spin_unlock(&journal->j_state_lock); } - jbd_free_handle(handle); + jbd2_free_handle(handle); return err; } diff --git a/fs/jffs2/debug.h b/fs/jffs2/debug.h index 2a49f2c..4130ada 100644 --- a/fs/jffs2/debug.h +++ b/fs/jffs2/debug.h @@ -80,28 +80,28 @@ #define JFFS2_ERROR(fmt, ...) \ do { \ printk(JFFS2_ERR_MSG_PREFIX \ - " (%d) %s: " fmt, current->pid, \ + " (%d) %s: " fmt, task_pid_nr(current), \ __FUNCTION__ , ##__VA_ARGS__); \ } while(0) #define JFFS2_WARNING(fmt, ...) \ do { \ printk(JFFS2_WARN_MSG_PREFIX \ - " (%d) %s: " fmt, current->pid, \ + " (%d) %s: " fmt, task_pid_nr(current), \ __FUNCTION__ , ##__VA_ARGS__); \ } while(0) #define JFFS2_NOTICE(fmt, ...) \ do { \ printk(JFFS2_NOTICE_MSG_PREFIX \ - " (%d) %s: " fmt, current->pid, \ + " (%d) %s: " fmt, task_pid_nr(current), \ __FUNCTION__ , ##__VA_ARGS__); \ } while(0) #define JFFS2_DEBUG(fmt, ...) \ do { \ printk(JFFS2_DBG_MSG_PREFIX \ - " (%d) %s: " fmt, current->pid, \ + " (%d) %s: " fmt, task_pid_nr(current), \ __FUNCTION__ , ##__VA_ARGS__); \ } while(0) @@ -1659,8 +1659,10 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) error = locks_verify_locked(inode); if (!error) { DQUOT_INIT(inode); - - error = do_truncate(dentry, 0, ATTR_MTIME|ATTR_CTIME, NULL); + + error = do_truncate(dentry, 0, + ATTR_MTIME|ATTR_CTIME|ATTR_OPEN, + NULL); } put_write_access(inode); if (error) diff --git a/fs/namespace.c b/fs/namespace.c index 07daa79..8607529 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1411,7 +1411,7 @@ long do_mount(char *dev_name, char *dir_name, char *type_page, mnt_flags |= MNT_RELATIME; flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | - MS_NOATIME | MS_NODIRATIME | MS_RELATIME); + MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT); /* ... and get the mountpoint */ retval = path_lookup(dir_name, LOOKUP_FOLLOW, &nd); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 6c22453..6d2f2a3 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -357,6 +357,10 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr) nfs_inc_stats(inode, NFSIOS_VFSSETATTR); + /* skip mode change if it's just for clearing setuid/setgid */ + if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) + attr->ia_valid &= ~ATTR_MODE; + if (attr->ia_valid & ATTR_SIZE) { if (!S_ISREG(inode->i_mode) || attr->ia_size == i_size_read(inode)) attr->ia_valid &= ~ATTR_SIZE; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 819545d..d019918 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -364,14 +364,23 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, if (iap->ia_valid & ATTR_MODE) { iap->ia_mode &= S_IALLUGO; imode = iap->ia_mode |= (imode & ~S_IALLUGO); + /* if changing uid/gid revoke setuid/setgid in mode */ + if ((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid) { + iap->ia_valid |= ATTR_KILL_PRIV; + iap->ia_mode &= ~S_ISUID; + } + if ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid) + iap->ia_mode &= ~S_ISGID; + } else { + /* + * Revoke setuid/setgid bit on chown/chgrp + */ + if ((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid) + iap->ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV; + if ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid) + iap->ia_valid |= ATTR_KILL_SGID; } - /* Revoke setuid/setgid bit on chown/chgrp */ - if ((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid) - iap->ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV; - if ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid) - iap->ia_valid |= ATTR_KILL_SGID; - /* Change the attributes. */ iap->ia_valid |= ATTR_CTIME; @@ -1020,13 +1029,13 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, if (EX_WGATHER(exp)) { if (atomic_read(&inode->i_writecount) > 1 || (last_ino == inode->i_ino && last_dev == inode->i_sb->s_dev)) { - dprintk("nfsd: write defer %d\n", current->pid); + dprintk("nfsd: write defer %d\n", task_pid_nr(current)); msleep(10); - dprintk("nfsd: write resume %d\n", current->pid); + dprintk("nfsd: write resume %d\n", task_pid_nr(current)); } if (inode->i_state & I_DIRTY) { - dprintk("nfsd: write sync %d\n", current->pid); + dprintk("nfsd: write sync %d\n", task_pid_nr(current)); host_err=nfsd_sync(file); } #if 0 diff --git a/fs/nls/nls_base.c b/fs/nls/nls_base.c index e790581..64965e1 100644 --- a/fs/nls/nls_base.c +++ b/fs/nls/nls_base.c @@ -111,7 +111,7 @@ utf8_wctomb(__u8 *s, wchar_t wc, int maxlen) int c, nc; const struct utf8_table *t; - if (s == 0) + if (!s) return 0; l = wc; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index f14b541..9cc7c04 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1372,7 +1372,7 @@ static ssize_t o2hb_region_pid_read(struct o2hb_region *reg, spin_lock(&o2hb_live_lock); if (reg->hr_task) - pid = reg->hr_task->pid; + pid = task_pid_nr(reg->hr_task); spin_unlock(&o2hb_live_lock); if (!pid) diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h index 75cd877..cd04606 100644 --- a/fs/ocfs2/cluster/masklog.h +++ b/fs/ocfs2/cluster/masklog.h @@ -192,7 +192,7 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits; * previous token if args expands to nothing. */ #define __mlog_printk(level, fmt, args...) \ - printk(level "(%u,%lu):%s:%d " fmt, current->pid, \ + printk(level "(%u,%lu):%s:%d " fmt, task_pid_nr(current), \ __mlog_cpu_guess, __PRETTY_FUNCTION__, __LINE__ , \ ##args) diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index a2c3316..2fde7bf 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -259,7 +259,7 @@ static void dlm_print_reco_node_status(struct dlm_ctxt *dlm) struct dlm_lock_resource *res; mlog(ML_NOTICE, "%s(%d): recovery info, state=%s, dead=%u, master=%u\n", - dlm->name, dlm->dlm_reco_thread_task->pid, + dlm->name, task_pid_nr(dlm->dlm_reco_thread_task), dlm->reco.state & DLM_RECO_STATE_ACTIVE ? "ACTIVE" : "inactive", dlm->reco.dead_node, dlm->reco.new_master); @@ -420,7 +420,7 @@ void dlm_wait_for_recovery(struct dlm_ctxt *dlm) if (dlm_in_recovery(dlm)) { mlog(0, "%s: reco thread %d in recovery: " "state=%d, master=%u, dead=%u\n", - dlm->name, dlm->dlm_reco_thread_task->pid, + dlm->name, task_pid_nr(dlm->dlm_reco_thread_task), dlm->reco.state, dlm->reco.new_master, dlm->reco.dead_node); } @@ -483,7 +483,7 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm) return 0; } mlog(0, "%s(%d):recovery thread found node %u in the recovery map!\n", - dlm->name, dlm->dlm_reco_thread_task->pid, + dlm->name, task_pid_nr(dlm->dlm_reco_thread_task), dlm->reco.dead_node); spin_unlock(&dlm->spinlock); @@ -507,7 +507,7 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm) mlog(0, "another node will master this recovery session.\n"); } mlog(0, "dlm=%s (%d), new_master=%u, this node=%u, dead_node=%u\n", - dlm->name, dlm->dlm_reco_thread_task->pid, dlm->reco.new_master, + dlm->name, task_pid_nr(dlm->dlm_reco_thread_task), dlm->reco.new_master, dlm->node_num, dlm->reco.dead_node); /* it is safe to start everything back up here @@ -520,7 +520,7 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm) master_here: mlog(0, "(%d) mastering recovery of %s:%u here(this=%u)!\n", - dlm->dlm_reco_thread_task->pid, + task_pid_nr(dlm->dlm_reco_thread_task), dlm->name, dlm->reco.dead_node, dlm->node_num); status = dlm_remaster_locks(dlm, dlm->reco.dead_node); diff --git a/fs/proc/array.c b/fs/proc/array.c index 27b59f5..63c95af 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -77,6 +77,7 @@ #include <linux/cpuset.h> #include <linux/rcupdate.h> #include <linux/delayacct.h> +#include <linux/pid_namespace.h> #include <asm/pgtable.h> #include <asm/processor.h> @@ -145,8 +146,7 @@ static inline const char *get_task_state(struct task_struct *tsk) TASK_UNINTERRUPTIBLE | TASK_STOPPED | TASK_TRACED)) | - (tsk->exit_state & (EXIT_ZOMBIE | - EXIT_DEAD)); + tsk->exit_state; const char **p = &task_state_array[0]; while (state) { @@ -161,8 +161,15 @@ static inline char *task_state(struct task_struct *p, char *buffer) struct group_info *group_info; int g; struct fdtable *fdt = NULL; + struct pid_namespace *ns; + pid_t ppid, tpid; + ns = current->nsproxy->pid_ns; rcu_read_lock(); + ppid = pid_alive(p) ? + task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0; + tpid = pid_alive(p) && p->ptrace ? + task_ppid_nr_ns(rcu_dereference(p->parent), ns) : 0; buffer += sprintf(buffer, "State:\t%s\n" "Tgid:\t%d\n" @@ -172,9 +179,9 @@ static inline char *task_state(struct task_struct *p, char *buffer) "Uid:\t%d\t%d\t%d\t%d\n" "Gid:\t%d\t%d\t%d\t%d\n", get_task_state(p), - p->tgid, p->pid, - pid_alive(p) ? rcu_dereference(p->real_parent)->tgid : 0, - pid_alive(p) && p->ptrace ? rcu_dereference(p->parent)->pid : 0, + task_tgid_nr_ns(p, ns), + task_pid_nr_ns(p, ns), + ppid, tpid, p->uid, p->euid, p->suid, p->fsuid, p->gid, p->egid, p->sgid, p->fsgid); @@ -394,6 +401,9 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole) unsigned long rsslim = 0; char tcomm[sizeof(task->comm)]; unsigned long flags; + struct pid_namespace *ns; + + ns = current->nsproxy->pid_ns; state = *get_task_state(task); vsize = eip = esp = 0; @@ -416,7 +426,7 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole) struct signal_struct *sig = task->signal; if (sig->tty) { - tty_pgrp = pid_nr(sig->tty->pgrp); + tty_pgrp = pid_nr_ns(sig->tty->pgrp, ns); tty_nr = new_encode_dev(tty_devnum(sig->tty)); } @@ -446,12 +456,12 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole) maj_flt += sig->maj_flt; utime = cputime_add(utime, sig->utime); stime = cputime_add(stime, sig->stime); - gtime += cputime_add(gtime, sig->gtime); + gtime = cputime_add(gtime, sig->gtime); } - sid = signal_session(sig); - pgid = process_group(task); - ppid = rcu_dereference(task->real_parent)->tgid; + sid = task_session_nr_ns(task, ns); + pgid = task_pgrp_nr_ns(task, ns); + ppid = task_ppid_nr_ns(task, ns); unlock_task_sighand(task, &flags); } @@ -483,7 +493,7 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole) res = sprintf(buffer, "%d (%s) %c %d %d %d %d %d %u %lu \ %lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \ %lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld\n", - task->pid, + task_pid_nr_ns(task, ns), tcomm, state, ppid, diff --git a/fs/proc/base.c b/fs/proc/base.c index 4fe74d1..39a3d7c 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -63,16 +63,19 @@ #include <linux/mm.h> #include <linux/rcupdate.h> #include <linux/kallsyms.h> +#include <linux/resource.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/ptrace.h> +#include <linux/cgroup.h> #include <linux/cpuset.h> #include <linux/audit.h> #include <linux/poll.h> #include <linux/nsproxy.h> #include <linux/oom.h> #include <linux/elf.h> +#include <linux/pid_namespace.h> #include "internal.h" /* NOTE: @@ -301,6 +304,78 @@ static int proc_oom_score(struct task_struct *task, char *buffer) return sprintf(buffer, "%lu\n", points); } +struct limit_names { + char *name; + char *unit; +}; + +static const struct limit_names lnames[RLIM_NLIMITS] = { + [RLIMIT_CPU] = {"Max cpu time", "ms"}, + [RLIMIT_FSIZE] = {"Max file size", "bytes"}, + [RLIMIT_DATA] = {"Max data size", "bytes"}, + [RLIMIT_STACK] = {"Max stack size", "bytes"}, + [RLIMIT_CORE] = {"Max core file size", "bytes"}, + [RLIMIT_RSS] = {"Max resident set", "bytes"}, + [RLIMIT_NPROC] = {"Max processes", "processes"}, + [RLIMIT_NOFILE] = {"Max open files", "files"}, + [RLIMIT_MEMLOCK] = {"Max locked memory", "bytes"}, + [RLIMIT_AS] = {"Max address space", "bytes"}, + [RLIMIT_LOCKS] = {"Max file locks", "locks"}, + [RLIMIT_SIGPENDING] = {"Max pending signals", "signals"}, + [RLIMIT_MSGQUEUE] = {"Max msgqueue size", "bytes"}, + [RLIMIT_NICE] = {"Max nice priority", NULL}, + [RLIMIT_RTPRIO] = {"Max realtime priority", NULL}, +}; + +/* Display limits for a process */ +static int proc_pid_limits(struct task_struct *task, char *buffer) +{ + unsigned int i; + int count = 0; + unsigned long flags; + char *bufptr = buffer; + + struct rlimit rlim[RLIM_NLIMITS]; + + rcu_read_lock(); + if (!lock_task_sighand(task,&flags)) { + rcu_read_unlock(); + return 0; + } + memcpy(rlim, task->signal->rlim, sizeof(struct rlimit) * RLIM_NLIMITS); + unlock_task_sighand(task, &flags); + rcu_read_unlock(); + + /* + * print the file header + */ + count += sprintf(&bufptr[count], "%-25s %-20s %-20s %-10s\n", + "Limit", "Soft Limit", "Hard Limit", "Units"); + + for (i = 0; i < RLIM_NLIMITS; i++) { + if (rlim[i].rlim_cur == RLIM_INFINITY) + count += sprintf(&bufptr[count], "%-25s %-20s ", + lnames[i].name, "unlimited"); + else + count += sprintf(&bufptr[count], "%-25s %-20lu ", + lnames[i].name, rlim[i].rlim_cur); + + if (rlim[i].rlim_max == RLIM_INFINITY) + count += sprintf(&bufptr[count], "%-20s ", "unlimited"); + else + count += sprintf(&bufptr[count], "%-20lu ", + rlim[i].rlim_max); + + if (lnames[i].unit) + count += sprintf(&bufptr[count], "%-10s\n", + lnames[i].unit); + else + count += sprintf(&bufptr[count], "\n"); + } + + return count; +} + /************************************************************************/ /* Here the fs part begins */ /************************************************************************/ @@ -349,18 +424,21 @@ struct proc_mounts { static int mounts_open(struct inode *inode, struct file *file) { struct task_struct *task = get_proc_task(inode); + struct nsproxy *nsp; struct mnt_namespace *ns = NULL; struct proc_mounts *p; int ret = -EINVAL; if (task) { - task_lock(task); - if (task->nsproxy) { - ns = task->nsproxy->mnt_ns; + rcu_read_lock(); + nsp = task_nsproxy(task); + if (nsp) { + ns = nsp->mnt_ns; if (ns) get_mnt_ns(ns); } - task_unlock(task); + rcu_read_unlock(); + put_task_struct(task); } @@ -423,16 +501,20 @@ static int mountstats_open(struct inode *inode, struct file *file) if (!ret) { struct seq_file *m = file->private_data; + struct nsproxy *nsp; struct mnt_namespace *mnt_ns = NULL; struct task_struct *task = get_proc_task(inode); if (task) { - task_lock(task); - if (task->nsproxy) - mnt_ns = task->nsproxy->mnt_ns; - if (mnt_ns) - get_mnt_ns(mnt_ns); - task_unlock(task); + rcu_read_lock(); + nsp = task_nsproxy(task); + if (nsp) { + mnt_ns = nsp->mnt_ns; + if (mnt_ns) + get_mnt_ns(mnt_ns); + } + rcu_read_unlock(); + put_task_struct(task); } @@ -1437,7 +1519,7 @@ static int proc_readfd_common(struct file * filp, void * dirent, struct dentry *dentry = filp->f_path.dentry; struct inode *inode = dentry->d_inode; struct task_struct *p = get_proc_task(inode); - unsigned int fd, tid, ino; + unsigned int fd, ino; int retval; struct files_struct * files; struct fdtable *fdt; @@ -1446,7 +1528,6 @@ static int proc_readfd_common(struct file * filp, void * dirent, if (!p) goto out_no_task; retval = 0; - tid = p->pid; fd = filp->f_pos; switch (fd) { @@ -1681,7 +1762,6 @@ static int proc_pident_readdir(struct file *filp, const struct pid_entry *ents, unsigned int nents) { int i; - int pid; struct dentry *dentry = filp->f_path.dentry; struct inode *inode = dentry->d_inode; struct task_struct *task = get_proc_task(inode); @@ -1694,7 +1774,6 @@ static int proc_pident_readdir(struct file *filp, goto out_no_task; ret = 0; - pid = task->pid; i = filp->f_pos; switch (i) { case 0: @@ -1928,14 +2007,14 @@ static int proc_self_readlink(struct dentry *dentry, char __user *buffer, int buflen) { char tmp[PROC_NUMBUF]; - sprintf(tmp, "%d", current->tgid); + sprintf(tmp, "%d", task_tgid_vnr(current)); return vfs_readlink(dentry,buffer,buflen,tmp); } static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd) { char tmp[PROC_NUMBUF]; - sprintf(tmp, "%d", current->tgid); + sprintf(tmp, "%d", task_tgid_vnr(current)); return ERR_PTR(vfs_follow_link(nd,tmp)); } @@ -2101,6 +2180,7 @@ static const struct pid_entry tgid_base_stuff[] = { REG("environ", S_IRUSR, environ), INF("auxv", S_IRUSR, pid_auxv), INF("status", S_IRUGO, pid_status), + INF("limits", S_IRUSR, pid_limits), #ifdef CONFIG_SCHED_DEBUG REG("sched", S_IRUGO|S_IWUSR, pid_sched), #endif @@ -2130,9 +2210,12 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_SCHEDSTATS INF("schedstat", S_IRUGO, pid_schedstat), #endif -#ifdef CONFIG_CPUSETS +#ifdef CONFIG_PROC_PID_CPUSET REG("cpuset", S_IRUGO, cpuset), #endif +#ifdef CONFIG_CGROUPS + REG("cgroup", S_IRUGO, cgroup), +#endif INF("oom_score", S_IRUGO, oom_score), REG("oom_adj", S_IRUGO|S_IWUSR, oom_adjust), #ifdef CONFIG_AUDITSYSCALL @@ -2193,27 +2276,27 @@ static const struct inode_operations proc_tgid_base_inode_operations = { * that no dcache entries will exist at process exit time it * just makes it very unlikely that any will persist. */ -void proc_flush_task(struct task_struct *task) +static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid) { struct dentry *dentry, *leader, *dir; char buf[PROC_NUMBUF]; struct qstr name; name.name = buf; - name.len = snprintf(buf, sizeof(buf), "%d", task->pid); - dentry = d_hash_and_lookup(proc_mnt->mnt_root, &name); + name.len = snprintf(buf, sizeof(buf), "%d", pid); + dentry = d_hash_and_lookup(mnt->mnt_root, &name); if (dentry) { shrink_dcache_parent(dentry); d_drop(dentry); dput(dentry); } - if (thread_group_leader(task)) + if (tgid == 0) goto out; name.name = buf; - name.len = snprintf(buf, sizeof(buf), "%d", task->tgid); - leader = d_hash_and_lookup(proc_mnt->mnt_root, &name); + name.len = snprintf(buf, sizeof(buf), "%d", tgid); + leader = d_hash_and_lookup(mnt->mnt_root, &name); if (!leader) goto out; @@ -2224,7 +2307,7 @@ void proc_flush_task(struct task_struct *task) goto out_put_leader; name.name = buf; - name.len = snprintf(buf, sizeof(buf), "%d", task->pid); + name.len = snprintf(buf, sizeof(buf), "%d", pid); dentry = d_hash_and_lookup(dir, &name); if (dentry) { shrink_dcache_parent(dentry); @@ -2239,6 +2322,36 @@ out: return; } +/* + * when flushing dentries from proc one need to flush them from global + * proc (proc_mnt) and from all the namespaces' procs this task was seen + * in. this call is supposed to make all this job. + */ + +void proc_flush_task(struct task_struct *task) +{ + int i, leader; + struct pid *pid, *tgid; + struct upid *upid; + + leader = thread_group_leader(task); + proc_flush_task_mnt(proc_mnt, task->pid, leader ? task->tgid : 0); + pid = task_pid(task); + if (pid->level == 0) + return; + + tgid = task_tgid(task); + for (i = 1; i <= pid->level; i++) { + upid = &pid->numbers[i]; + proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr, + leader ? 0 : tgid->numbers[i].nr); + } + + upid = &pid->numbers[pid->level]; + if (upid->nr == 1) + pid_ns_release_proc(upid->ns); +} + static struct dentry *proc_pid_instantiate(struct inode *dir, struct dentry * dentry, struct task_struct *task, const void *ptr) @@ -2274,6 +2387,7 @@ struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct struct dentry *result = ERR_PTR(-ENOENT); struct task_struct *task; unsigned tgid; + struct pid_namespace *ns; result = proc_base_lookup(dir, dentry); if (!IS_ERR(result) || PTR_ERR(result) != -ENOENT) @@ -2283,8 +2397,9 @@ struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct if (tgid == ~0U) goto out; + ns = dentry->d_sb->s_fs_info; rcu_read_lock(); - task = find_task_by_pid(tgid); + task = find_task_by_pid_ns(tgid, ns); if (task) get_task_struct(task); rcu_read_unlock(); @@ -2301,7 +2416,8 @@ out: * Find the first task with tgid >= tgid * */ -static struct task_struct *next_tgid(unsigned int tgid) +static struct task_struct *next_tgid(unsigned int tgid, + struct pid_namespace *ns) { struct task_struct *task; struct pid *pid; @@ -2309,9 +2425,9 @@ static struct task_struct *next_tgid(unsigned int tgid) rcu_read_lock(); retry: task = NULL; - pid = find_ge_pid(tgid); + pid = find_ge_pid(tgid, ns); if (pid) { - tgid = pid->nr + 1; + tgid = pid_nr_ns(pid, ns) + 1; task = pid_task(pid, PIDTYPE_PID); /* What we to know is if the pid we have find is the * pid of a thread_group_leader. Testing for task @@ -2351,6 +2467,7 @@ int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir) struct task_struct *reaper = get_proc_task(filp->f_path.dentry->d_inode); struct task_struct *task; int tgid; + struct pid_namespace *ns; if (!reaper) goto out_no_task; @@ -2361,11 +2478,12 @@ int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir) goto out; } + ns = filp->f_dentry->d_sb->s_fs_info; tgid = filp->f_pos - TGID_OFFSET; - for (task = next_tgid(tgid); + for (task = next_tgid(tgid, ns); task; - put_task_struct(task), task = next_tgid(tgid + 1)) { - tgid = task->pid; + put_task_struct(task), task = next_tgid(tgid + 1, ns)) { + tgid = task_pid_nr_ns(task, ns); filp->f_pos = tgid + TGID_OFFSET; if (proc_pid_fill_cache(filp, dirent, filldir, task, tgid) < 0) { put_task_struct(task); @@ -2388,6 +2506,7 @@ static const struct pid_entry tid_base_stuff[] = { REG("environ", S_IRUSR, environ), INF("auxv", S_IRUSR, pid_auxv), INF("status", S_IRUGO, pid_status), + INF("limits", S_IRUSR, pid_limits), #ifdef CONFIG_SCHED_DEBUG REG("sched", S_IRUGO|S_IWUSR, pid_sched), #endif @@ -2416,9 +2535,12 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_SCHEDSTATS INF("schedstat", S_IRUGO, pid_schedstat), #endif -#ifdef CONFIG_CPUSETS +#ifdef CONFIG_PROC_PID_CPUSET REG("cpuset", S_IRUGO, cpuset), #endif +#ifdef CONFIG_CGROUPS + REG("cgroup", S_IRUGO, cgroup), +#endif INF("oom_score", S_IRUGO, oom_score), REG("oom_adj", S_IRUGO|S_IWUSR, oom_adjust), #ifdef CONFIG_AUDITSYSCALL @@ -2486,6 +2608,7 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry struct task_struct *task; struct task_struct *leader = get_proc_task(dir); unsigned tid; + struct pid_namespace *ns; if (!leader) goto out_no_task; @@ -2494,14 +2617,15 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry if (tid == ~0U) goto out; + ns = dentry->d_sb->s_fs_info; rcu_read_lock(); - task = find_task_by_pid(tid); + task = find_task_by_pid_ns(tid, ns); if (task) get_task_struct(task); rcu_read_unlock(); if (!task) goto out; - if (leader->tgid != task->tgid) + if (!same_thread_group(leader, task)) goto out_drop_task; result = proc_task_instantiate(dir, dentry, task, NULL); @@ -2526,14 +2650,14 @@ out_no_task: * threads past it. */ static struct task_struct *first_tid(struct task_struct *leader, - int tid, int nr) + int tid, int nr, struct pid_namespace *ns) { struct task_struct *pos; rcu_read_lock(); /* Attempt to start with the pid of a thread */ if (tid && (nr > 0)) { - pos = find_task_by_pid(tid); + pos = find_task_by_pid_ns(tid, ns); if (pos && (pos->group_leader == leader)) goto found; } @@ -2602,6 +2726,7 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi ino_t ino; int tid; unsigned long pos = filp->f_pos; /* avoiding "long long" filp->f_pos */ + struct pid_namespace *ns; task = get_proc_task(inode); if (!task) @@ -2635,12 +2760,13 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi /* f_version caches the tgid value that the last readdir call couldn't * return. lseek aka telldir automagically resets f_version to 0. */ + ns = filp->f_dentry->d_sb->s_fs_info; tid = (int)filp->f_version; filp->f_version = 0; - for (task = first_tid(leader, tid, pos - 2); + for (task = first_tid(leader, tid, pos - 2, ns); task; task = next_tid(task), pos++) { - tid = task->pid; + tid = task_pid_nr_ns(task, ns); if (proc_task_fill_cache(filp, dirent, filldir, task, tid) < 0) { /* returning this tgid failed, save it as the first * pid for the next readir call */ diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 99ca004..abe6a3f 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -448,7 +448,7 @@ out_mod: return NULL; } -int proc_fill_super(struct super_block *s, void *data, int silent) +int proc_fill_super(struct super_block *s) { struct inode * root_inode; diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index d6dc72c..e0d064e 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -91,7 +91,8 @@ static int loadavg_read_proc(char *page, char **start, off_t off, LOAD_INT(a), LOAD_FRAC(a), LOAD_INT(b), LOAD_FRAC(b), LOAD_INT(c), LOAD_FRAC(c), - nr_running(), nr_threads, current->nsproxy->pid_ns->last_pid); + nr_running(), nr_threads, + task_active_pid_ns(current)->last_pid); return proc_calc_metrics(page, start, off, count, eof, len); } diff --git a/fs/proc/root.c b/fs/proc/root.c index cf30466..ec9cb3b 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -18,32 +18,90 @@ #include <linux/bitops.h> #include <linux/smp_lock.h> #include <linux/mount.h> +#include <linux/pid_namespace.h> #include "internal.h" struct proc_dir_entry *proc_bus, *proc_root_fs, *proc_root_driver; +static int proc_test_super(struct super_block *sb, void *data) +{ + return sb->s_fs_info == data; +} + +static int proc_set_super(struct super_block *sb, void *data) +{ + struct pid_namespace *ns; + + ns = (struct pid_namespace *)data; + sb->s_fs_info = get_pid_ns(ns); + return set_anon_super(sb, NULL); +} + static int proc_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, struct vfsmount *mnt) { + int err; + struct super_block *sb; + struct pid_namespace *ns; + struct proc_inode *ei; + if (proc_mnt) { /* Seed the root directory with a pid so it doesn't need * to be special in base.c. I would do this earlier but * the only task alive when /proc is mounted the first time * is the init_task and it doesn't have any pids. */ - struct proc_inode *ei; ei = PROC_I(proc_mnt->mnt_sb->s_root->d_inode); if (!ei->pid) ei->pid = find_get_pid(1); } - return get_sb_single(fs_type, flags, data, proc_fill_super, mnt); + + if (flags & MS_KERNMOUNT) + ns = (struct pid_namespace *)data; + else + ns = current->nsproxy->pid_ns; + + sb = sget(fs_type, proc_test_super, proc_set_super, ns); + if (IS_ERR(sb)) + return PTR_ERR(sb); + + if (!sb->s_root) { + sb->s_flags = flags; + err = proc_fill_super(sb); + if (err) { + up_write(&sb->s_umount); + deactivate_super(sb); + return err; + } + + ei = PROC_I(sb->s_root->d_inode); + if (!ei->pid) { + rcu_read_lock(); + ei->pid = get_pid(find_pid_ns(1, ns)); + rcu_read_unlock(); + } + + sb->s_flags |= MS_ACTIVE; + ns->proc_mnt = mnt; + } + + return simple_set_mnt(mnt, sb); +} + +static void proc_kill_sb(struct super_block *sb) +{ + struct pid_namespace *ns; + + ns = (struct pid_namespace *)sb->s_fs_info; + kill_anon_super(sb); + put_pid_ns(ns); } static struct file_system_type proc_fs_type = { .name = "proc", .get_sb = proc_get_sb, - .kill_sb = kill_anon_super, + .kill_sb = proc_kill_sb, }; void __init proc_root_init(void) @@ -54,12 +112,13 @@ void __init proc_root_init(void) err = register_filesystem(&proc_fs_type); if (err) return; - proc_mnt = kern_mount(&proc_fs_type); + proc_mnt = kern_mount_data(&proc_fs_type, &init_pid_ns); err = PTR_ERR(proc_mnt); if (IS_ERR(proc_mnt)) { unregister_filesystem(&proc_fs_type); return; } + proc_misc_init(); proc_net_init(); @@ -153,6 +212,22 @@ struct proc_dir_entry proc_root = { .parent = &proc_root, }; +int pid_ns_prepare_proc(struct pid_namespace *ns) +{ + struct vfsmount *mnt; + + mnt = kern_mount_data(&proc_fs_type, ns); + if (IS_ERR(mnt)) + return PTR_ERR(mnt); + + return 0; +} + +void pid_ns_release_proc(struct pid_namespace *ns) +{ + mntput(ns->proc_mnt); +} + EXPORT_SYMBOL(proc_symlink); EXPORT_SYMBOL(proc_mkdir); EXPORT_SYMBOL(create_proc_entry); diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c index 2a5dd34..16b331d 100644 --- a/fs/reiserfs/bitmap.c +++ b/fs/reiserfs/bitmap.c @@ -47,7 +47,9 @@ test_bit(_ALLOC_ ## optname , &SB_ALLOC_OPTS(s)) static inline void get_bit_address(struct super_block *s, - b_blocknr_t block, int *bmap_nr, int *offset) + b_blocknr_t block, + unsigned int *bmap_nr, + unsigned int *offset) { /* It is in the bitmap block number equal to the block * number divided by the number of bits in a block. */ @@ -56,10 +58,10 @@ static inline void get_bit_address(struct super_block *s, *offset = block & ((s->s_blocksize << 3) - 1); } -#ifdef CONFIG_REISERFS_CHECK int is_reusable(struct super_block *s, b_blocknr_t block, int bit_value) { - int bmap, offset; + unsigned int bmap, offset; + unsigned int bmap_count = reiserfs_bmap_count(s); if (block == 0 || block >= SB_BLOCK_COUNT(s)) { reiserfs_warning(s, @@ -75,25 +77,26 @@ int is_reusable(struct super_block *s, b_blocknr_t block, int bit_value) if (unlikely(test_bit(REISERFS_OLD_FORMAT, &(REISERFS_SB(s)->s_properties)))) { b_blocknr_t bmap1 = REISERFS_SB(s)->s_sbh->b_blocknr + 1; - if (block >= bmap1 && block <= bmap1 + SB_BMAP_NR(s)) { + if (block >= bmap1 && + block <= bmap1 + bmap_count) { reiserfs_warning(s, "vs: 4019: is_reusable: " "bitmap block %lu(%u) can't be freed or reused", - block, SB_BMAP_NR(s)); + block, bmap_count); return 0; } } else { if (offset == 0) { reiserfs_warning(s, "vs: 4020: is_reusable: " "bitmap block %lu(%u) can't be freed or reused", - block, SB_BMAP_NR(s)); + block, bmap_count); return 0; } } - if (bmap >= SB_BMAP_NR(s)) { + if (bmap >= bmap_count) { reiserfs_warning(s, "vs-4030: is_reusable: there is no so many bitmap blocks: " - "block=%lu, bitmap_nr=%d", block, bmap); + "block=%lu, bitmap_nr=%u", block, bmap); return 0; } @@ -106,12 +109,11 @@ int is_reusable(struct super_block *s, b_blocknr_t block, int bit_value) return 1; } -#endif /* CONFIG_REISERFS_CHECK */ /* searches in journal structures for a given block number (bmap, off). If block is found in reiserfs journal it suggests next free block candidate to test. */ -static inline int is_block_in_journal(struct super_block *s, int bmap, int - off, int *next) +static inline int is_block_in_journal(struct super_block *s, unsigned int bmap, + int off, int *next) { b_blocknr_t tmp; @@ -132,8 +134,8 @@ static inline int is_block_in_journal(struct super_block *s, int bmap, int /* it searches for a window of zero bits with given minimum and maximum lengths in one bitmap * block; */ static int scan_bitmap_block(struct reiserfs_transaction_handle *th, - int bmap_n, int *beg, int boundary, int min, - int max, int unfm) + unsigned int bmap_n, int *beg, int boundary, + int min, int max, int unfm) { struct super_block *s = th->t_super; struct reiserfs_bitmap_info *bi = &SB_AP_BITMAP(s)[bmap_n]; @@ -143,8 +145,8 @@ static int scan_bitmap_block(struct reiserfs_transaction_handle *th, BUG_ON(!th->t_trans_id); - RFALSE(bmap_n >= SB_BMAP_NR(s), "Bitmap %d is out of range (0..%d)", - bmap_n, SB_BMAP_NR(s) - 1); + RFALSE(bmap_n >= reiserfs_bmap_count(s), "Bitmap %u is out of " + "range (0..%u)", bmap_n, reiserfs_bmap_count(s) - 1); PROC_INFO_INC(s, scan_bitmap.bmap); /* this is unclear and lacks comments, explain how journal bitmaps work here for the reader. Convey a sense of the design here. What @@ -249,12 +251,12 @@ static int bmap_hash_id(struct super_block *s, u32 id) } else { hash_in = (char *)(&id); hash = keyed_hash(hash_in, 4); - bm = hash % SB_BMAP_NR(s); + bm = hash % reiserfs_bmap_count(s); if (!bm) bm = 1; } /* this can only be true when SB_BMAP_NR = 1 */ - if (bm >= SB_BMAP_NR(s)) + if (bm >= reiserfs_bmap_count(s)) bm = 0; return bm; } @@ -273,7 +275,7 @@ static inline int block_group_used(struct super_block *s, u32 id) * to make a better decision. This favors long-term performace gain * with a better on-disk layout vs. a short term gain of skipping the * read and potentially having a bad placement. */ - if (info->first_zero_hint == 0) { + if (info->free_count == UINT_MAX) { struct buffer_head *bh = reiserfs_read_bitmap_block(s, bm); brelse(bh); } @@ -309,16 +311,16 @@ __le32 reiserfs_choose_packing(struct inode * dir) * bitmap and place new blocks there. Returns number of allocated blocks. */ static int scan_bitmap(struct reiserfs_transaction_handle *th, b_blocknr_t * start, b_blocknr_t finish, - int min, int max, int unfm, unsigned long file_block) + int min, int max, int unfm, sector_t file_block) { int nr_allocated = 0; struct super_block *s = th->t_super; /* find every bm and bmap and bmap_nr in this file, and change them all to bitmap_blocknr * - Hans, it is not a block number - Zam. */ - int bm, off; - int end_bm, end_off; - int off_max = s->s_blocksize << 3; + unsigned int bm, off; + unsigned int end_bm, end_off; + unsigned int off_max = s->s_blocksize << 3; BUG_ON(!th->t_trans_id); @@ -328,10 +330,10 @@ static int scan_bitmap(struct reiserfs_transaction_handle *th, get_bit_address(s, *start, &bm, &off); get_bit_address(s, finish, &end_bm, &end_off); - if (bm > SB_BMAP_NR(s)) + if (bm > reiserfs_bmap_count(s)) return 0; - if (end_bm > SB_BMAP_NR(s)) - end_bm = SB_BMAP_NR(s); + if (end_bm > reiserfs_bmap_count(s)) + end_bm = reiserfs_bmap_count(s); /* When the bitmap is more than 10% free, anyone can allocate. * When it's less than 10% free, only files that already use the @@ -385,7 +387,7 @@ static void _reiserfs_free_block(struct reiserfs_transaction_handle *th, struct reiserfs_super_block *rs; struct buffer_head *sbh, *bmbh; struct reiserfs_bitmap_info *apbi; - int nr, offset; + unsigned int nr, offset; BUG_ON(!th->t_trans_id); @@ -397,10 +399,12 @@ static void _reiserfs_free_block(struct reiserfs_transaction_handle *th, get_bit_address(s, block, &nr, &offset); - if (nr >= sb_bmap_nr(rs)) { + if (nr >= reiserfs_bmap_count(s)) { reiserfs_warning(s, "vs-4075: reiserfs_free_block: " - "block %lu is out of range on %s", - block, reiserfs_bdevname(s)); + "block %lu is out of range on %s " + "(nr=%u,max=%u)", block, + reiserfs_bdevname(s), nr, + reiserfs_bmap_count(s)); return; } @@ -434,12 +438,19 @@ void reiserfs_free_block(struct reiserfs_transaction_handle *th, int for_unformatted) { struct super_block *s = th->t_super; - BUG_ON(!th->t_trans_id); RFALSE(!s, "vs-4061: trying to free block on nonexistent device"); - RFALSE(is_reusable(s, block, 1) == 0, - "vs-4071: can not free such block"); + if (!is_reusable(s, block, 1)) + return; + + if (block > sb_block_count(REISERFS_SB(s)->s_rs)) { + reiserfs_panic(th->t_super, "bitmap-4072", + "Trying to free block outside file system " + "boundaries (%lu > %lu)", + block, sb_block_count(REISERFS_SB(s)->s_rs)); + return; + } /* mark it before we clear it, just in case */ journal_mark_freed(th, s, block); _reiserfs_free_block(th, inode, block, for_unformatted); @@ -449,11 +460,11 @@ void reiserfs_free_block(struct reiserfs_transaction_handle *th, static void reiserfs_free_prealloc_block(struct reiserfs_transaction_handle *th, struct inode *inode, b_blocknr_t block) { + BUG_ON(!th->t_trans_id); RFALSE(!th->t_super, "vs-4060: trying to free block on nonexistent device"); - RFALSE(is_reusable(th->t_super, block, 1) == 0, - "vs-4070: can not free such block"); - BUG_ON(!th->t_trans_id); + if (!is_reusable(th->t_super, block, 1)) + return; _reiserfs_free_block(th, inode, block, 1); } @@ -1207,27 +1218,22 @@ void reiserfs_cache_bitmap_metadata(struct super_block *sb, { unsigned long *cur = (unsigned long *)(bh->b_data + bh->b_size); - info->first_zero_hint = 1 << (sb->s_blocksize_bits + 3); + /* The first bit must ALWAYS be 1 */ + BUG_ON(!reiserfs_test_le_bit(0, (unsigned long *)bh->b_data)); + + info->free_count = 0; while (--cur >= (unsigned long *)bh->b_data) { - int base = ((char *)cur - bh->b_data) << 3; + int i; /* 0 and ~0 are special, we can optimize for them */ - if (*cur == 0) { - info->first_zero_hint = base; + if (*cur == 0) info->free_count += BITS_PER_LONG; - } else if (*cur != ~0L) { /* A mix, investigate */ - int b; - for (b = BITS_PER_LONG - 1; b >= 0; b--) { - if (!reiserfs_test_le_bit(b, cur)) { - info->first_zero_hint = base + b; + else if (*cur != ~0L) /* A mix, investigate */ + for (i = BITS_PER_LONG - 1; i >= 0; i--) + if (!reiserfs_test_le_bit(i, cur)) info->free_count++; - } - } - } } - /* The first bit must ALWAYS be 1 */ - BUG_ON(info->first_zero_hint == 0); } struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb, @@ -1257,7 +1263,7 @@ struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb, BUG_ON(!buffer_uptodate(bh)); BUG_ON(atomic_read(&bh->b_count) == 0); - if (info->first_zero_hint == 0) + if (info->free_count == UINT_MAX) reiserfs_cache_bitmap_metadata(sb, bh, info); } @@ -1267,12 +1273,13 @@ struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb, int reiserfs_init_bitmap_cache(struct super_block *sb) { struct reiserfs_bitmap_info *bitmap; + unsigned int bmap_nr = reiserfs_bmap_count(sb); - bitmap = vmalloc(sizeof (*bitmap) * SB_BMAP_NR(sb)); + bitmap = vmalloc(sizeof(*bitmap) * bmap_nr); if (bitmap == NULL) return -ENOMEM; - memset(bitmap, 0, sizeof (*bitmap) * SB_BMAP_NR(sb)); + memset(bitmap, 0xff, sizeof(*bitmap) * bmap_nr); SB_AP_BITMAP(sb) = bitmap; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 9ea1200..a991af9 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -199,7 +199,7 @@ static inline void set_block_dev_mapped(struct buffer_head *bh, // files which were created in the earlier version can not be longer, // than 2 gb // -static int file_capable(struct inode *inode, long block) +static int file_capable(struct inode *inode, sector_t block) { if (get_inode_item_key_version(inode) != KEY_FORMAT_3_5 || // it is new file. block < (1 << (31 - inode->i_sb->s_blocksize_bits))) // old file, but 'block' is inside of 2gb @@ -242,7 +242,7 @@ static int restart_transaction(struct reiserfs_transaction_handle *th, // Please improve the english/clarity in the comment above, as it is // hard to understand. -static int _get_block_create_0(struct inode *inode, long block, +static int _get_block_create_0(struct inode *inode, sector_t block, struct buffer_head *bh_result, int args) { INITIALIZE_PATH(path); @@ -250,7 +250,7 @@ static int _get_block_create_0(struct inode *inode, long block, struct buffer_head *bh; struct item_head *ih, tmp_ih; int fs_gen; - int blocknr; + b_blocknr_t blocknr; char *p = NULL; int chars; int ret; @@ -569,7 +569,7 @@ static int convert_tail_for_hole(struct inode *inode, } static inline int _allocate_block(struct reiserfs_transaction_handle *th, - long block, + sector_t block, struct inode *inode, b_blocknr_t * allocated_block_nr, struct treepath *path, int flags) @@ -3061,7 +3061,11 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = dentry->d_inode; int error; - unsigned int ia_valid = attr->ia_valid; + unsigned int ia_valid; + + /* must be turned off for recursive notify_change calls */ + ia_valid = attr->ia_valid &= ~(ATTR_KILL_SUID|ATTR_KILL_SGID); + reiserfs_write_lock(inode->i_sb); if (attr->ia_valid & ATTR_SIZE) { /* version 2 items will be caught by the s_maxbytes check diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 4cad9e7..bb05a3e 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -219,11 +219,12 @@ static void allocate_bitmap_nodes(struct super_block *p_s_sb) } } -static int set_bit_in_list_bitmap(struct super_block *p_s_sb, int block, +static int set_bit_in_list_bitmap(struct super_block *p_s_sb, + b_blocknr_t block, struct reiserfs_list_bitmap *jb) { - int bmap_nr = block / (p_s_sb->s_blocksize << 3); - int bit_nr = block % (p_s_sb->s_blocksize << 3); + unsigned int bmap_nr = block / (p_s_sb->s_blocksize << 3); + unsigned int bit_nr = block % (p_s_sb->s_blocksize << 3); if (!jb->bitmaps[bmap_nr]) { jb->bitmaps[bmap_nr] = get_bitmap_node(p_s_sb); @@ -239,7 +240,7 @@ static void cleanup_bitmap_list(struct super_block *p_s_sb, if (jb->bitmaps == NULL) return; - for (i = 0; i < SB_BMAP_NR(p_s_sb); i++) { + for (i = 0; i < reiserfs_bmap_count(p_s_sb); i++) { if (jb->bitmaps[i]) { free_bitmap_node(p_s_sb, jb->bitmaps[i]); jb->bitmaps[i] = NULL; @@ -289,7 +290,7 @@ static int free_bitmap_nodes(struct super_block *p_s_sb) */ int reiserfs_allocate_list_bitmaps(struct super_block *p_s_sb, struct reiserfs_list_bitmap *jb_array, - int bmap_nr) + unsigned int bmap_nr) { int i; int failed = 0; @@ -483,7 +484,7 @@ static inline struct reiserfs_journal_cnode *get_journal_hash_dev(struct ** */ int reiserfs_in_journal(struct super_block *p_s_sb, - int bmap_nr, int bit_nr, int search_all, + unsigned int bmap_nr, int bit_nr, int search_all, b_blocknr_t * next_zero_bit) { struct reiserfs_journal *journal = SB_JOURNAL(p_s_sb); @@ -1013,7 +1014,7 @@ static int flush_commit_list(struct super_block *s, struct reiserfs_journal_list *jl, int flushall) { int i; - int bn; + b_blocknr_t bn; struct buffer_head *tbh = NULL; unsigned long trans_id = jl->j_trans_id; struct reiserfs_journal *journal = SB_JOURNAL(s); @@ -2307,8 +2308,9 @@ static int journal_read_transaction(struct super_block *p_s_sb, Right now it is only used from journal code. But later we might use it from other places. Note: Do not use journal_getblk/sb_getblk functions here! */ -static struct buffer_head *reiserfs_breada(struct block_device *dev, int block, - int bufsize, unsigned int max_block) +static struct buffer_head *reiserfs_breada(struct block_device *dev, + b_blocknr_t block, int bufsize, + b_blocknr_t max_block) { struct buffer_head *bhlist[BUFNR]; unsigned int blocks = BUFNR; @@ -2732,7 +2734,7 @@ int journal_init(struct super_block *p_s_sb, const char *j_dev_name, journal->j_persistent_trans = 0; if (reiserfs_allocate_list_bitmaps(p_s_sb, journal->j_list_bitmap, - SB_BMAP_NR(p_s_sb))) + reiserfs_bmap_count(p_s_sb))) goto free_and_return; allocate_bitmap_nodes(p_s_sb); @@ -2740,7 +2742,7 @@ int journal_init(struct super_block *p_s_sb, const char *j_dev_name, SB_JOURNAL_1st_RESERVED_BLOCK(p_s_sb) = (old_format ? REISERFS_OLD_DISK_OFFSET_IN_BYTES / p_s_sb->s_blocksize + - SB_BMAP_NR(p_s_sb) + + reiserfs_bmap_count(p_s_sb) + 1 : REISERFS_DISK_OFFSET_IN_BYTES / p_s_sb->s_blocksize + 2); diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c index bc808a9..5e7388b 100644 --- a/fs/reiserfs/prints.c +++ b/fs/reiserfs/prints.c @@ -356,13 +356,11 @@ extern struct tree_balance *cur_tb; void reiserfs_panic(struct super_block *sb, const char *fmt, ...) { do_reiserfs_warning(fmt); - printk(KERN_EMERG "REISERFS: panic (device %s): %s\n", - reiserfs_bdevname(sb), error_buf); - BUG(); - /* this is not actually called, but makes reiserfs_panic() "noreturn" */ - panic("REISERFS: panic (device %s): %s\n", - reiserfs_bdevname(sb), error_buf); + dump_stack(); + + panic(KERN_EMERG "REISERFS: panic (device %s): %s\n", + reiserfs_bdevname(sb), error_buf); } void reiserfs_abort(struct super_block *sb, int errno, const char *fmt, ...) diff --git a/fs/reiserfs/resize.c b/fs/reiserfs/resize.c index 976cc78..f71c394 100644 --- a/fs/reiserfs/resize.c +++ b/fs/reiserfs/resize.c @@ -61,7 +61,8 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new) } /* count used bits in last bitmap block */ - block_r = SB_BLOCK_COUNT(s) - (SB_BMAP_NR(s) - 1) * s->s_blocksize * 8; + block_r = SB_BLOCK_COUNT(s) - + (reiserfs_bmap_count(s) - 1) * s->s_blocksize * 8; /* count bitmap blocks in new fs */ bmap_nr_new = block_count_new / (s->s_blocksize * 8); @@ -73,7 +74,7 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new) /* save old values */ block_count = SB_BLOCK_COUNT(s); - bmap_nr = SB_BMAP_NR(s); + bmap_nr = reiserfs_bmap_count(s); /* resizing of reiserfs bitmaps (journal and real), if needed */ if (bmap_nr_new > bmap_nr) { @@ -119,7 +120,7 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new) return -ENOMEM; } memset(bitmap, 0, - sizeof(struct reiserfs_bitmap_info) * SB_BMAP_NR(s)); + sizeof(struct reiserfs_bitmap_info) * bmap_nr_new); for (i = 0; i < bmap_nr; i++) bitmap[i] = old_bitmap[i]; @@ -143,7 +144,6 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new) mark_buffer_dirty(bh); sync_dirty_buffer(bh); // update bitmap_info stuff - bitmap[i].first_zero_hint = 1; bitmap[i].free_count = sb_blocksize(sb) * 8 - 1; brelse(bh); } @@ -173,8 +173,6 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new) for (i = block_r; i < s->s_blocksize * 8; i++) reiserfs_test_and_clear_le_bit(i, bh->b_data); info->free_count += s->s_blocksize * 8 - block_r; - if (!info->first_zero_hint) - info->first_zero_hint = block_r; journal_mark_dirty(&th, s, bh); brelse(bh); @@ -196,9 +194,6 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new) brelse(bh); info->free_count -= s->s_blocksize * 8 - block_r_new; - /* Extreme case where last bitmap is the only valid block in itself. */ - if (!info->free_count) - info->first_zero_hint = 0; /* update super */ reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1); free_blocks = SB_FREE_BLOCKS(s); @@ -206,7 +201,7 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new) free_blocks + (block_count_new - block_count - (bmap_nr_new - bmap_nr))); PUT_SB_BLOCK_COUNT(s, block_count_new); - PUT_SB_BMAP_NR(s, bmap_nr_new); + PUT_SB_BMAP_NR(s, bmap_would_wrap(bmap_nr_new) ? : bmap_nr_new); s->s_dirt = 1; journal_mark_dirty(&th, s, SB_BUFFER_WITH_SB(s)); diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index 981027d..ca41567 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -559,7 +559,7 @@ static int is_tree_node(struct buffer_head *bh, int level) /* The function is NOT SCHEDULE-SAFE! */ static void search_by_key_reada(struct super_block *s, struct buffer_head **bh, - unsigned long *b, int num) + b_blocknr_t *b, int num) { int i, j; @@ -611,7 +611,7 @@ int search_by_key(struct super_block *p_s_sb, const struct cpu_key *p_s_key, /* DISK_LEAF_NODE_LEVEL */ ) { - int n_block_number; + b_blocknr_t n_block_number; int expected_level; struct buffer_head *p_s_bh; struct path_element *p_s_last_element; @@ -619,7 +619,7 @@ int search_by_key(struct super_block *p_s_sb, const struct cpu_key *p_s_key, /* int right_neighbor_of_leaf_node; int fs_gen; struct buffer_head *reada_bh[SEARCH_BY_KEY_READA]; - unsigned long reada_blocks[SEARCH_BY_KEY_READA]; + b_blocknr_t reada_blocks[SEARCH_BY_KEY_READA]; int reada_count = 0; #ifdef CONFIG_REISERFS_CHECK diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index b82897a..57adfe9 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1725,6 +1725,21 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) set_sb_umount_state(rs, REISERFS_ERROR_FS); set_sb_fs_state(rs, 0); + /* Clear out s_bmap_nr if it would wrap. We can handle this + * case, but older revisions can't. This will cause the + * file system to fail mount on those older implementations, + * avoiding corruption. -jeffm */ + if (bmap_would_wrap(reiserfs_bmap_count(s)) && + sb_bmap_nr(rs) != 0) { + reiserfs_warning(s, "super-2030: This file system " + "claims to use %u bitmap blocks in " + "its super block, but requires %u. " + "Clearing to zero.", sb_bmap_nr(rs), + reiserfs_bmap_count(s)); + + set_sb_bmap_nr(rs, 0); + } + if (old_format_only(s)) { /* filesystem of format 3.5 either with standard or non-standard journal */ diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index fab4b9b..1597f6b 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -484,7 +484,7 @@ reiserfs_xattr_set(struct inode *inode, const char *name, const void *buffer, /* Resize it so we're ok to write there */ newattrs.ia_size = buffer_size; newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME; - mutex_lock(&xinode->i_mutex); + mutex_lock_nested(&xinode->i_mutex, I_MUTEX_XATTR); err = notify_change(fp->f_path.dentry, &newattrs); if (err) goto out_filp; @@ -1223,7 +1223,8 @@ int reiserfs_xattr_init(struct super_block *s, int mount_flags) if (!IS_ERR(dentry)) { if (!(mount_flags & MS_RDONLY) && !dentry->d_inode) { struct inode *inode = dentry->d_parent->d_inode; - mutex_lock(&inode->i_mutex); + mutex_lock_nested(&inode->i_mutex, + I_MUTEX_XATTR); err = inode->i_op->mkdir(inode, dentry, 0700); mutex_unlock(&inode->i_mutex); if (err) { diff --git a/fs/select.c b/fs/select.c index 7dede89..47f4792 100644 --- a/fs/select.c +++ b/fs/select.c @@ -177,11 +177,6 @@ get_max: return max; } -#define BIT(i) (1UL << ((i)&(__NFDBITS-1))) -#define MEM(i,m) ((m)+(unsigned)(i)/__NFDBITS) -#define ISSET(i,m) (((i)&*(m)) != 0) -#define SET(i,m) (*(m) |= (i)) - #define POLLIN_SET (POLLRDNORM | POLLRDBAND | POLLIN | POLLHUP | POLLERR) #define POLLOUT_SET (POLLWRBAND | POLLWRNORM | POLLOUT | POLLERR) #define POLLEX_SET (POLLPRI) @@ -40,10 +40,6 @@ #include <asm/uaccess.h> -void get_filesystem(struct file_system_type *fs); -void put_filesystem(struct file_system_type *fs); -struct file_system_type *get_fs_type(const char *name); - LIST_HEAD(super_blocks); DEFINE_SPINLOCK(sb_lock); @@ -336,21 +332,21 @@ struct super_block *sget(struct file_system_type *type, void *data) { struct super_block *s = NULL; - struct list_head *p; + struct super_block *old; int err; retry: spin_lock(&sb_lock); - if (test) list_for_each(p, &type->fs_supers) { - struct super_block *old; - old = list_entry(p, struct super_block, s_instances); - if (!test(old, data)) - continue; - if (!grab_super(old)) - goto retry; - if (s) - destroy_super(s); - return old; + if (test) { + list_for_each_entry(old, &type->fs_supers, s_instances) { + if (!test(old, data)) + continue; + if (!grab_super(old)) + goto retry; + if (s) + destroy_super(s); + return old; + } } if (!s) { spin_unlock(&sb_lock); @@ -948,9 +944,9 @@ do_kern_mount(const char *fstype, int flags, const char *name, void *data) return mnt; } -struct vfsmount *kern_mount(struct file_system_type *type) +struct vfsmount *kern_mount_data(struct file_system_type *type, void *data) { - return vfs_kern_mount(type, 0, type->name, NULL); + return vfs_kern_mount(type, MS_KERNMOUNT, type->name, data); } -EXPORT_SYMBOL(kern_mount); +EXPORT_SYMBOL_GPL(kern_mount_data); diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c index 726449d..3586c7a 100644 --- a/fs/xfs/linux-2.6/xfs_export.c +++ b/fs/xfs/linux-2.6/xfs_export.c @@ -54,8 +54,8 @@ xfs_fs_decode_fh( struct dentry *de), void *context) { - xfs_fid2_t ifid; - xfs_fid2_t pfid; + xfs_fid_t ifid; + xfs_fid_t pfid; void *parent = NULL; int is64 = 0; __u32 *p = fh; @@ -144,7 +144,7 @@ xfs_fs_get_dentry( struct dentry *result; int error; - error = xfs_vget(XFS_M(sb), &vp, (fid_t *)data); + error = xfs_vget(XFS_M(sb), &vp, data); if (error || vp == NULL) return ERR_PTR(-ESTALE) ; diff --git a/fs/xfs/linux-2.6/xfs_export.h b/fs/xfs/linux-2.6/xfs_export.h index e794ca4..2f36071 100644 --- a/fs/xfs/linux-2.6/xfs_export.h +++ b/fs/xfs/linux-2.6/xfs_export.h @@ -71,13 +71,13 @@ xfs_fileid_length(int hasparent, int is64) /* * Decode encoded inode information (either for the inode itself - * or the parent) into an xfs_fid2_t structure. Advances and + * or the parent) into an xfs_fid_t structure. Advances and * returns the new data pointer */ static inline __u32 * -xfs_fileid_decode_fid2(__u32 *p, xfs_fid2_t *fid, int is64) +xfs_fileid_decode_fid2(__u32 *p, xfs_fid_t *fid, int is64) { - fid->fid_len = sizeof(xfs_fid2_t) - sizeof(fid->fid_len); + fid->fid_len = sizeof(xfs_fid_t) - sizeof(fid->fid_len); fid->fid_pad = 0; fid->fid_ino = *p++; #if XFS_BIG_INUMS diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c index ffec630..2b34bad 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl.c +++ b/fs/xfs/linux-2.6/xfs_ioctl.c @@ -152,11 +152,11 @@ xfs_find_handle( lock_mode = xfs_ilock_map_shared(ip); /* fill in fid section of handle from inode */ - handle.ha_fid.xfs_fid_len = sizeof(xfs_fid_t) - - sizeof(handle.ha_fid.xfs_fid_len); - handle.ha_fid.xfs_fid_pad = 0; - handle.ha_fid.xfs_fid_gen = ip->i_d.di_gen; - handle.ha_fid.xfs_fid_ino = ip->i_ino; + handle.ha_fid.fid_len = sizeof(xfs_fid_t) - + sizeof(handle.ha_fid.fid_len); + handle.ha_fid.fid_pad = 0; + handle.ha_fid.fid_gen = ip->i_d.di_gen; + handle.ha_fid.fid_ino = ip->i_ino; xfs_iunlock_map_shared(ip, lock_mode); @@ -222,10 +222,10 @@ xfs_vget_fsop_handlereq( if (hlen < sizeof(*handlep)) memset(((char *)handlep) + hlen, 0, sizeof(*handlep) - hlen); if (hlen > sizeof(handlep->ha_fsid)) { - if (handlep->ha_fid.xfs_fid_len != - (hlen - sizeof(handlep->ha_fsid) - - sizeof(handlep->ha_fid.xfs_fid_len)) - || handlep->ha_fid.xfs_fid_pad) + if (handlep->ha_fid.fid_len != + (hlen - sizeof(handlep->ha_fsid) - + sizeof(handlep->ha_fid.fid_len)) || + handlep->ha_fid.fid_pad) return XFS_ERROR(EINVAL); } @@ -233,9 +233,9 @@ xfs_vget_fsop_handlereq( * Crack the handle, obtain the inode # & generation # */ xfid = (struct xfs_fid *)&handlep->ha_fid; - if (xfid->xfs_fid_len == sizeof(*xfid) - sizeof(xfid->xfs_fid_len)) { - ino = xfid->xfs_fid_ino; - igen = xfid->xfs_fid_gen; + if (xfid->fid_len == sizeof(*xfid) - sizeof(xfid->fid_len)) { + ino = xfid->fid_ino; + igen = xfid->fid_gen; } else { return XFS_ERROR(EINVAL); } diff --git a/fs/xfs/xfs_dmops.c b/fs/xfs/xfs_dmops.c index 6cd5704..a1e55fb 100644 --- a/fs/xfs/xfs_dmops.c +++ b/fs/xfs/xfs_dmops.c @@ -41,29 +41,16 @@ int xfs_dmops_get(struct xfs_mount *mp, struct xfs_mount_args *args) { if (args->flags & XFSMNT_DMAPI) { - struct xfs_dmops *ops; - - ops = symbol_get(xfs_dmcore_xfs); - if (!ops) { - request_module("xfs_dmapi"); - ops = symbol_get(xfs_dmcore_xfs); - } - - if (!ops) { - cmn_err(CE_WARN, "XFS: no dmapi support available."); - return EINVAL; - } - mp->m_dm_ops = ops; - } else { - mp->m_dm_ops = &xfs_dmcore_stub; + cmn_err(CE_WARN, + "XFS: dmapi support not available in this kernel."); + return EINVAL; } + mp->m_dm_ops = &xfs_dmcore_stub; return 0; } void xfs_dmops_put(struct xfs_mount *mp) { - if (mp->m_dm_ops != &xfs_dmcore_stub) - symbol_put(xfs_dmcore_xfs); } diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h index ec3c9c2..aab9662 100644 --- a/fs/xfs/xfs_fs.h +++ b/fs/xfs/xfs_fs.h @@ -389,30 +389,13 @@ typedef struct xfs_fsop_attrmulti_handlereq { */ typedef struct { __u32 val[2]; } xfs_fsid_t; /* file system id type */ - -#ifndef HAVE_FID -#define MAXFIDSZ 46 - -typedef struct fid { - __u16 fid_len; /* length of data in bytes */ - unsigned char fid_data[MAXFIDSZ]; /* data (fid_len worth) */ -} fid_t; -#endif - typedef struct xfs_fid { - __u16 xfs_fid_len; /* length of remainder */ - __u16 xfs_fid_pad; - __u32 xfs_fid_gen; /* generation number */ - __u64 xfs_fid_ino; /* 64 bits inode number */ + __u16 fid_len; /* length of remainder */ + __u16 fid_pad; + __u32 fid_gen; /* generation number */ + __u64 fid_ino; /* 64 bits inode number */ } xfs_fid_t; -typedef struct xfs_fid2 { - __u16 fid_len; /* length of remainder */ - __u16 fid_pad; /* padding, must be zero */ - __u32 fid_gen; /* generation number */ - __u64 fid_ino; /* inode number */ -} xfs_fid2_t; - typedef struct xfs_handle { union { __s64 align; /* force alignment of ha_fid */ @@ -422,9 +405,9 @@ typedef struct xfs_handle { } xfs_handle_t; #define ha_fsid ha_u._ha_fsid -#define XFS_HSIZE(handle) (((char *) &(handle).ha_fid.xfs_fid_pad \ +#define XFS_HSIZE(handle) (((char *) &(handle).ha_fid.fid_pad \ - (char *) &(handle)) \ - + (handle).ha_fid.xfs_fid_len) + + (handle).ha_fid.fid_len) /* * Flags for going down operation diff --git a/fs/xfs/xfs_qmops.c b/fs/xfs/xfs_qmops.c index c266a01..2ec1d8a 100644 --- a/fs/xfs/xfs_qmops.c +++ b/fs/xfs/xfs_qmops.c @@ -135,19 +135,13 @@ int xfs_qmops_get(struct xfs_mount *mp, struct xfs_mount_args *args) { if (args->flags & (XFSMNT_UQUOTA | XFSMNT_PQUOTA | XFSMNT_GQUOTA)) { - struct xfs_qmops *ops; - - ops = symbol_get(xfs_qmcore_xfs); - if (!ops) { - request_module("xfs_quota"); - ops = symbol_get(xfs_qmcore_xfs); - } - - if (!ops) { - cmn_err(CE_WARN, "XFS: no quota support available."); - return EINVAL; - } - mp->m_qm_ops = ops; +#ifdef CONFIG_XFS_QUOTA + mp->m_qm_ops = &xfs_qmcore_xfs; +#else + cmn_err(CE_WARN, + "XFS: qouta support not available in this kernel."); + return EINVAL; +#endif } else { mp->m_qm_ops = &xfs_qmcore_stub; } @@ -158,6 +152,4 @@ xfs_qmops_get(struct xfs_mount *mp, struct xfs_mount_args *args) void xfs_qmops_put(struct xfs_mount *mp) { - if (mp->m_qm_ops != &xfs_qmcore_stub) - symbol_put(xfs_qmcore_xfs); } diff --git a/fs/xfs/xfs_vfsops.c b/fs/xfs/xfs_vfsops.c index a5a8454..a154459 100644 --- a/fs/xfs/xfs_vfsops.c +++ b/fs/xfs/xfs_vfsops.c @@ -1635,9 +1635,8 @@ int xfs_vget( xfs_mount_t *mp, bhv_vnode_t **vpp, - fid_t *fidp) + xfs_fid_t *xfid) { - xfs_fid_t *xfid = (struct xfs_fid *)fidp; xfs_inode_t *ip; int error; xfs_ino_t ino; @@ -1647,11 +1646,11 @@ xfs_vget( * Invalid. Since handles can be created in user space and passed in * via gethandle(), this is not cause for a panic. */ - if (xfid->xfs_fid_len != sizeof(*xfid) - sizeof(xfid->xfs_fid_len)) + if (xfid->fid_len != sizeof(*xfid) - sizeof(xfid->fid_len)) return XFS_ERROR(EINVAL); - ino = xfid->xfs_fid_ino; - igen = xfid->xfs_fid_gen; + ino = xfid->fid_ino; + igen = xfid->fid_gen; /* * NFS can sometimes send requests for ino 0. Fail them gracefully. diff --git a/fs/xfs/xfs_vfsops.h b/fs/xfs/xfs_vfsops.h index bc99e3e..a592fe0 100644 --- a/fs/xfs/xfs_vfsops.h +++ b/fs/xfs/xfs_vfsops.h @@ -2,7 +2,7 @@ #define _XFS_VFSOPS_H 1 struct cred; -struct fid; +struct xfs_fid; struct inode; struct kstatfs; struct xfs_mount; @@ -17,7 +17,7 @@ int xfs_root(struct xfs_mount *mp, bhv_vnode_t **vpp); int xfs_statvfs(struct xfs_mount *mp, struct kstatfs *statp, bhv_vnode_t *vp); int xfs_sync(struct xfs_mount *mp, int flags); -int xfs_vget(struct xfs_mount *mp, bhv_vnode_t **vpp, struct fid *fidp); +int xfs_vget(struct xfs_mount *mp, bhv_vnode_t **vpp, struct xfs_fid *xfid); int xfs_parseargs(struct xfs_mount *mp, char *options, struct xfs_mount_args *args, int update); int xfs_showargs(struct xfs_mount *mp, struct seq_file *m); diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c index 5e3c57c..efd5aff 100644 --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -3466,23 +3466,14 @@ std_return: } -/* - * xfs_fid2 - * - * A fid routine that takes a pointer to a previously allocated - * fid structure (like xfs_fast_fid) but uses a 64 bit inode number. - */ int xfs_fid2( xfs_inode_t *ip, - fid_t *fidp) + xfs_fid_t *xfid) { - xfs_fid2_t *xfid = (xfs_fid2_t *)fidp; - vn_trace_entry(ip, __FUNCTION__, (inst_t *)__return_address); - ASSERT(sizeof(fid_t) >= sizeof(xfs_fid2_t)); - xfid->fid_len = sizeof(xfs_fid2_t) - sizeof(xfid->fid_len); + xfid->fid_len = sizeof(xfs_fid_t) - sizeof(xfid->fid_len); xfid->fid_pad = 0; /* * use memcpy because the inode is a long long and there's no diff --git a/fs/xfs/xfs_vnodeops.h b/fs/xfs/xfs_vnodeops.h index f36e74f..b7e461c 100644 --- a/fs/xfs/xfs_vnodeops.h +++ b/fs/xfs/xfs_vnodeops.h @@ -39,7 +39,7 @@ int xfs_readdir(struct xfs_inode *dp, void *dirent, size_t bufsize, int xfs_symlink(struct xfs_inode *dp, bhv_vname_t *dentry, char *target_path, mode_t mode, bhv_vnode_t **vpp, struct cred *credp); -int xfs_fid2(struct xfs_inode *ip, fid_t *fidp); +int xfs_fid2(struct xfs_inode *ip, struct xfs_fid *xfid); int xfs_rwlock(struct xfs_inode *ip, bhv_vrwlock_t locktype); void xfs_rwunlock(struct xfs_inode *ip, bhv_vrwlock_t locktype); int xfs_inode_flush(struct xfs_inode *ip, int flags); |