diff options
Diffstat (limited to 'fs')
42 files changed, 456 insertions, 520 deletions
diff --git a/fs/afs/Kconfig b/fs/afs/Kconfig index 5c4e61d3c772..8f975f25b486 100644 --- a/fs/afs/Kconfig +++ b/fs/afs/Kconfig @@ -2,6 +2,7 @@ config AFS_FS tristate "Andrew File System support (AFS) (EXPERIMENTAL)" depends on INET && EXPERIMENTAL select AF_RXRPC + select DNS_RESOLVER help If you say Y here, you will get an experimental Andrew File System driver. It currently only supports unsecured read-only AFS access. diff --git a/fs/afs/cell.c b/fs/afs/cell.c index e19c13f059ed..ffea35c63879 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -13,6 +13,7 @@ #include <linux/slab.h> #include <linux/key.h> #include <linux/ctype.h> +#include <linux/dns_resolver.h> #include <linux/sched.h> #include <keys/rxrpc-type.h> #include "internal.h" @@ -36,6 +37,8 @@ static struct afs_cell *afs_cell_alloc(const char *name, char *vllist) struct key *key; size_t namelen; char keyname[4 + AFS_MAXCELLNAME + 1], *cp, *dp, *next; + char *dvllist = NULL, *_vllist = NULL; + char delimiter = ':'; int ret; _enter("%s,%s", name, vllist); @@ -43,8 +46,10 @@ static struct afs_cell *afs_cell_alloc(const char *name, char *vllist) BUG_ON(!name); /* TODO: want to look up "this cell" in the cache */ namelen = strlen(name); - if (namelen > AFS_MAXCELLNAME) + if (namelen > AFS_MAXCELLNAME) { + _leave(" = -ENAMETOOLONG"); return ERR_PTR(-ENAMETOOLONG); + } /* allocate and initialise a cell record */ cell = kzalloc(sizeof(struct afs_cell) + namelen + 1, GFP_KERNEL); @@ -64,15 +69,31 @@ static struct afs_cell *afs_cell_alloc(const char *name, char *vllist) INIT_LIST_HEAD(&cell->vl_list); spin_lock_init(&cell->vl_lock); + /* if the ip address is invalid, try dns query */ + if (!vllist || strlen(vllist) < 7) { + ret = dns_query("afsdb", name, namelen, "ipv4", &dvllist, NULL); + if (ret < 0) { + _leave(" = %d", ret); + return ERR_PTR(ret); + } + _vllist = dvllist; + + /* change the delimiter for user-space reply */ + delimiter = ','; + + } else { + _vllist = vllist; + } + /* fill in the VL server list from the rest of the string */ do { unsigned a, b, c, d; - next = strchr(vllist, ':'); + next = strchr(_vllist, delimiter); if (next) *next++ = 0; - if (sscanf(vllist, "%u.%u.%u.%u", &a, &b, &c, &d) != 4) + if (sscanf(_vllist, "%u.%u.%u.%u", &a, &b, &c, &d) != 4) goto bad_address; if (a > 255 || b > 255 || c > 255 || d > 255) @@ -81,7 +102,7 @@ static struct afs_cell *afs_cell_alloc(const char *name, char *vllist) cell->vl_addrs[cell->vl_naddrs++].s_addr = htonl((a << 24) | (b << 16) | (c << 8) | d); - } while (cell->vl_naddrs < AFS_CELL_MAX_ADDRS && (vllist = next)); + } while (cell->vl_naddrs < AFS_CELL_MAX_ADDRS && (_vllist = next)); /* create a key to represent an anonymous user */ memcpy(keyname, "afs@", 4); @@ -110,6 +131,7 @@ bad_address: ret = -EINVAL; error: key_put(cell->anonymous_key); + kfree(dvllist); kfree(cell); _leave(" = %d", ret); return ERR_PTR(ret); @@ -201,14 +223,12 @@ int afs_cell_init(char *rootcell) } cp = strchr(rootcell, ':'); - if (!cp) { - printk(KERN_ERR "kAFS: no VL server IP addresses specified\n"); - _leave(" = -EINVAL"); - return -EINVAL; - } + if (!cp) + _debug("kAFS: no VL server IP addresses specified"); + else + *cp++ = 0; /* allocate a cell record for the root cell */ - *cp++ = 0; new_root = afs_cell_create(rootcell, cp); if (IS_ERR(new_root)) { _leave(" = %ld", PTR_ERR(new_root)); @@ -1277,7 +1277,7 @@ out: /* sys_io_destroy: * Destroy the aio_context specified. May cancel any outstanding * AIOs and block on completion. Will fail with -ENOSYS if not - * implemented. May fail with -EFAULT if the context pointed to + * implemented. May fail with -EINVAL if the context pointed to * is invalid. */ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) @@ -1795,15 +1795,16 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, /* io_getevents: * Attempts to read at least min_nr events and up to nr events from - * the completion queue for the aio_context specified by ctx_id. May - * fail with -EINVAL if ctx_id is invalid, if min_nr is out of range, - * if nr is out of range, if when is out of range. May fail with - * -EFAULT if any of the memory specified to is invalid. May return - * 0 or < min_nr if no events are available and the timeout specified - * by when has elapsed, where when == NULL specifies an infinite - * timeout. Note that the timeout pointed to by when is relative and - * will be updated if not NULL and the operation blocks. Will fail - * with -ENOSYS if not implemented. + * the completion queue for the aio_context specified by ctx_id. If + * it succeeds, the number of read events is returned. May fail with + * -EINVAL if ctx_id is invalid, if min_nr is out of range, if nr is + * out of range, if timeout is out of range. May fail with -EFAULT + * if any of the memory specified is invalid. May return 0 or + * < min_nr if the timeout specified by timeout has elapsed + * before sufficient events are available, where timeout == NULL + * specifies an infinite timeout. Note that the timeout pointed to by + * timeout is relative and will be updated if not NULL and the + * operation blocks. Will fail with -ENOSYS if not implemented. */ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id, long, min_nr, diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index f4a7840bf42c..42c7fafc8bfe 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -37,9 +37,9 @@ void __cachefiles_printk_object(struct cachefiles_object *object, printk(KERN_ERR "%sobject: OBJ%x\n", prefix, object->fscache.debug_id); - printk(KERN_ERR "%sobjstate=%s fl=%lx swfl=%lx ev=%lx[%lx]\n", + printk(KERN_ERR "%sobjstate=%s fl=%lx wbusy=%x ev=%lx[%lx]\n", prefix, fscache_object_states[object->fscache.state], - object->fscache.flags, object->fscache.work.flags, + object->fscache.flags, work_busy(&object->fscache.work), object->fscache.events, object->fscache.event_mask & FSCACHE_OBJECT_EVENTS_MASK); printk(KERN_ERR "%sops=%u inp=%u exc=%u\n", @@ -212,7 +212,7 @@ wait_for_old_object: /* if the object we're waiting for is queued for processing, * then just put ourselves on the queue behind it */ - if (slow_work_is_queued(&xobject->fscache.work)) { + if (work_pending(&xobject->fscache.work)) { _debug("queue OBJ%x behind OBJ%x immediately", object->fscache.debug_id, xobject->fscache.debug_id); @@ -220,8 +220,7 @@ wait_for_old_object: } /* otherwise we sleep until either the object we're waiting for - * is done, or the slow-work facility wants the thread back to - * do other work */ + * is done, or the fscache_object is congested */ wq = bit_waitqueue(&xobject->flags, CACHEFILES_OBJECT_ACTIVE); init_wait(&wait); requeue = false; @@ -229,8 +228,8 @@ wait_for_old_object: prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); if (!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) break; - requeue = slow_work_sleep_till_thread_needed( - &object->fscache.work, &timeout); + + requeue = fscache_object_sleep_till_congested(&timeout); } while (timeout > 0 && !requeue); finish_wait(wq, &wait); diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 0f0d41fbb03f..0e3c0924cc3a 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -422,7 +422,7 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op, shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits; op->op.flags &= FSCACHE_OP_KEEP_FLAGS; - op->op.flags |= FSCACHE_OP_FAST; + op->op.flags |= FSCACHE_OP_ASYNC; op->op.processor = cachefiles_read_copier; pagevec_init(&pagevec, 0); @@ -729,7 +729,7 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op, pagevec_init(&pagevec, 0); op->op.flags &= FSCACHE_OP_KEEP_FLAGS; - op->op.flags |= FSCACHE_OP_FAST; + op->op.flags |= FSCACHE_OP_ASYNC; op->op.processor = cachefiles_read_copier; INIT_LIST_HEAD(&backpages); diff --git a/fs/char_dev.c b/fs/char_dev.c index d6db933df2b2..f80a4f25123c 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -20,6 +20,7 @@ #include <linux/cdev.h> #include <linux/mutex.h> #include <linux/backing-dev.h> +#include <linux/tty.h> #include "internal.h" diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index 5739fd7f88b4..917b7d449bb2 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -2,7 +2,6 @@ config CIFS tristate "CIFS support (advanced network filesystem, SMBFS successor)" depends on INET select NLS - select SLOW_WORK help This is the client VFS module for the Common Internet File System (CIFS) protocol which is the successor to the Server Message Block @@ -71,14 +70,14 @@ config CIFS_WEAK_PW_HASH If unsure, say N. config CIFS_UPCALL - bool "Kerberos/SPNEGO advanced session setup" - depends on CIFS && KEYS - help - Enables an upcall mechanism for CIFS which accesses - userspace helper utilities to provide SPNEGO packaged (RFC 4178) - Kerberos tickets which are needed to mount to certain secure servers - (for which more secure Kerberos authentication is required). If - unsure, say N. + bool "Kerberos/SPNEGO advanced session setup" + depends on CIFS && KEYS + select DNS_RESOLVER + help + Enables an upcall mechanism for CIFS which accesses userspace helper + utilities to provide SPNEGO packaged (RFC 4178) Kerberos tickets + which are needed to mount to certain secure servers (for which more + secure Kerberos authentication is required). If unsure, say N. config CIFS_XATTR bool "CIFS extended attributes" @@ -122,6 +121,7 @@ config CIFS_DEBUG2 config CIFS_DFS_UPCALL bool "DFS feature support" depends on CIFS && KEYS + select DNS_RESOLVER help Distributed File System (DFS) support is used to access shares transparently in an enterprise name space, even if the share diff --git a/fs/cifs/README b/fs/cifs/README index a727b7cb075f..a7081eeeb85d 100644 --- a/fs/cifs/README +++ b/fs/cifs/README @@ -568,8 +568,9 @@ module can be displayed via modinfo. Misc /proc/fs/cifs Flags and Debug Info ======================================= Informational pseudo-files: -DebugData Displays information about active CIFS sessions - and shares, as well as the cifs.ko version. +DebugData Displays information about active CIFS sessions and + shares, features enabled as well as the cifs.ko + version. Stats Lists summary resource usage information as well as per share statistics, if CONFIG_CIFS_STATS in enabled in the kernel configuration. diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 4fce6e61b34e..eb1ba493489f 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -119,6 +119,31 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) "Display Internal CIFS Data Structures for Debugging\n" "---------------------------------------------------\n"); seq_printf(m, "CIFS Version %s\n", CIFS_VERSION); + seq_printf(m, "Features: "); +#ifdef CONFIG_CIFS_DFS_UPCALL + seq_printf(m, "dfs"); + seq_putc(m, ' '); +#endif +#ifdef CONFIG_CIFS_FSCACHE + seq_printf(m, "fscache"); + seq_putc(m, ' '); +#endif +#ifdef CONFIG_CIFS_WEAK_PW_HASH + seq_printf(m, "lanman"); + seq_putc(m, ' '); +#endif +#ifdef CONFIG_CIFS_POSIX + seq_printf(m, "posix"); + seq_putc(m, ' '); +#endif +#ifdef CONFIG_CIFS_UPCALL + seq_printf(m, "spnego"); + seq_putc(m, ' '); +#endif +#ifdef CONFIG_CIFS_XATTR + seq_printf(m, "xattr"); +#endif + seq_putc(m, '\n'); seq_printf(m, "Active VFS Requests: %d\n", GlobalTotalActiveXid); seq_printf(m, "Servers:"); diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index dc1ed50ea06e..d6ced7aa23cf 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -141,7 +141,7 @@ char *cifs_compose_mount_options(const char *sb_mountdata, } rc = dns_resolve_server_name_to_ip(*devname, &srvIP); - if (rc != 0) { + if (rc < 0) { cERROR(1, "%s: Failed to resolve server part of %s to IP: %d", __func__, *devname, rc); goto compose_mount_options_err; @@ -150,8 +150,7 @@ char *cifs_compose_mount_options(const char *sb_mountdata, * assuming that we have 'unc=' and 'ip=' in * the original sb_mountdata */ - md_len = strlen(sb_mountdata) + strlen(srvIP) + - strlen(ref->node_name) + 12; + md_len = strlen(sb_mountdata) + rc + strlen(ref->node_name) + 12; mountdata = kzalloc(md_len+1, GFP_KERNEL); if (mountdata == NULL) { rc = -ENOMEM; diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c index 6effccff85a5..87044906cd1f 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/cifs/cifs_spnego.c @@ -84,6 +84,9 @@ struct key_type cifs_spnego_key_type = { /* strlen of ";uid=0x" */ #define UID_KEY_LEN 7 +/* strlen of ";creduid=0x" */ +#define CREDUID_KEY_LEN 11 + /* strlen of ";user=" */ #define USER_KEY_LEN 6 @@ -107,6 +110,7 @@ cifs_get_spnego_key(struct cifsSesInfo *sesInfo) IP_KEY_LEN + INET6_ADDRSTRLEN + MAX_MECH_STR_LEN + UID_KEY_LEN + (sizeof(uid_t) * 2) + + CREDUID_KEY_LEN + (sizeof(uid_t) * 2) + USER_KEY_LEN + strlen(sesInfo->userName) + PID_KEY_LEN + (sizeof(pid_t) * 2) + 1; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 8a2cf129e535..a5ed10c9afef 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -45,7 +45,6 @@ #include "cifs_fs_sb.h" #include <linux/mm.h> #include <linux/key-type.h> -#include "dns_resolve.h" #include "cifs_spnego.h" #include "fscache.h" #define CIFS_MAGIC_NUMBER 0xFF534D42 /* the first four bytes of SMB PDUs */ @@ -934,27 +933,13 @@ init_cifs(void) if (rc) goto out_unregister_filesystem; #endif -#ifdef CONFIG_CIFS_DFS_UPCALL - rc = cifs_init_dns_resolver(); - if (rc) - goto out_unregister_key_type; -#endif - rc = slow_work_register_user(THIS_MODULE); - if (rc) - goto out_unregister_resolver_key; return 0; - out_unregister_resolver_key: -#ifdef CONFIG_CIFS_DFS_UPCALL - cifs_exit_dns_resolver(); - out_unregister_key_type: -#endif #ifdef CONFIG_CIFS_UPCALL - unregister_key_type(&cifs_spnego_key_type); out_unregister_filesystem: -#endif unregister_filesystem(&cifs_fs_type); +#endif out_destroy_request_bufs: cifs_destroy_request_bufs(); out_destroy_mids: @@ -976,7 +961,6 @@ exit_cifs(void) cifs_fscache_unregister(); #ifdef CONFIG_CIFS_DFS_UPCALL cifs_dfs_release_automount_timer(); - cifs_exit_dns_resolver(); #endif #ifdef CONFIG_CIFS_UPCALL unregister_key_type(&cifs_spnego_key_type); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 59906146ad36..0cdfb8c32ac6 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -22,7 +22,7 @@ #include <linux/in.h> #include <linux/in6.h> #include <linux/slab.h> -#include <linux/slow-work.h> +#include <linux/workqueue.h> #include "cifs_fs_sb.h" #include "cifsacl.h" /* @@ -356,7 +356,7 @@ struct cifsFileInfo { atomic_t count; /* reference count */ struct mutex fh_mutex; /* prevents reopen race after dead ses*/ struct cifs_search_info srch_inf; - struct slow_work oplock_break; /* slow_work job for oplock breaks */ + struct work_struct oplock_break; /* work for oplock breaks */ }; /* Take a reference on the file private data */ @@ -728,6 +728,10 @@ GLOBAL_EXTERN unsigned int cifs_min_rcv; /* min size of big ntwrk buf pool */ GLOBAL_EXTERN unsigned int cifs_min_small; /* min size of small buf pool */ GLOBAL_EXTERN unsigned int cifs_max_pending; /* MAX requests at once to server*/ +void cifs_oplock_break(struct work_struct *work); +void cifs_oplock_break_get(struct cifsFileInfo *cfile); +void cifs_oplock_break_put(struct cifsFileInfo *cfile); + extern const struct slow_work_ops cifs_oplock_break_ops; #endif /* _CIFS_GLOB_H */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 2eaebbd31132..1f5450814087 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -86,8 +86,8 @@ extern unsigned int smbCalcSize(struct smb_hdr *ptr); extern unsigned int smbCalcSize_LE(struct smb_hdr *ptr); extern int decode_negTokenInit(unsigned char *security_blob, int length, struct TCP_Server_Info *server); -extern int cifs_convert_address(struct sockaddr *dst, char *src); -extern int cifs_fill_sockaddr(struct sockaddr *dst, char *src, +extern int cifs_convert_address(struct sockaddr *dst, const char *src, int len); +extern int cifs_fill_sockaddr(struct sockaddr *dst, const char *src, int len, unsigned short int port); extern int map_smb_to_linux_error(struct smb_hdr *smb, int logErr); extern void header_assemble(struct smb_hdr *, char /* command */ , diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 2a43a0aca965..95c2ea67edfb 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1543,6 +1543,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info) if (volume_info->UNCip && volume_info->UNC) { rc = cifs_fill_sockaddr((struct sockaddr *)&addr, volume_info->UNCip, + strlen(volume_info->UNCip), volume_info->port); if (!rc) { /* we failed translating address */ diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index a7de5e9fff11..578d88c5b46e 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -157,7 +157,7 @@ cifs_new_fileinfo(struct inode *newinode, __u16 fileHandle, mutex_init(&pCifsFile->lock_mutex); INIT_LIST_HEAD(&pCifsFile->llist); atomic_set(&pCifsFile->count, 1); - slow_work_init(&pCifsFile->oplock_break, &cifs_oplock_break_ops); + INIT_WORK(&pCifsFile->oplock_break, cifs_oplock_break); write_lock(&GlobalSMBSeslock); list_add(&pCifsFile->tlist, &cifs_sb->tcon->openFileList); diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c index 3ad7f4300c45..0eb87026cad3 100644 --- a/fs/cifs/dns_resolve.c +++ b/fs/cifs/dns_resolve.c @@ -4,6 +4,8 @@ * Copyright (c) 2007 Igor Mammedov * Author(s): Igor Mammedov (niallain@gmail.com) * Steve French (sfrench@us.ibm.com) + * Wang Lei (wang840925@gmail.com) + * David Howells (dhowells@redhat.com) * * Contains the CIFS DFS upcall routines used for hostname to * IP address translation. @@ -24,214 +26,73 @@ */ #include <linux/slab.h> -#include <linux/keyctl.h> -#include <linux/key-type.h> -#include <keys/user-type.h> +#include <linux/dns_resolver.h> #include "dns_resolve.h" #include "cifsglob.h" #include "cifsproto.h" #include "cifs_debug.h" -static const struct cred *dns_resolver_cache; - -/* Checks if supplied name is IP address - * returns: - * 1 - name is IP - * 0 - name is not IP - */ -static int -is_ip(char *name) -{ - struct sockaddr_storage ss; - - return cifs_convert_address((struct sockaddr *)&ss, name); -} - -static int -dns_resolver_instantiate(struct key *key, const void *data, - size_t datalen) -{ - int rc = 0; - char *ip; - - ip = kmalloc(datalen + 1, GFP_KERNEL); - if (!ip) - return -ENOMEM; - - memcpy(ip, data, datalen); - ip[datalen] = '\0'; - - /* make sure this looks like an address */ - if (!is_ip(ip)) { - kfree(ip); - return -EINVAL; - } - - key->type_data.x[0] = datalen; - key->payload.data = ip; - - return rc; -} - -static void -dns_resolver_destroy(struct key *key) -{ - kfree(key->payload.data); -} - -struct key_type key_type_dns_resolver = { - .name = "dns_resolver", - .def_datalen = sizeof(struct in_addr), - .describe = user_describe, - .instantiate = dns_resolver_instantiate, - .destroy = dns_resolver_destroy, - .match = user_match, -}; - -/* Resolves server name to ip address. - * input: - * unc - server UNC - * output: - * *ip_addr - pointer to server ip, caller responcible for freeing it. - * return 0 on success +/** + * dns_resolve_server_name_to_ip - Resolve UNC server name to ip address. + * @unc: UNC path specifying the server + * @ip_addr: Where to return the IP address. + * + * The IP address will be returned in string form, and the caller is + * responsible for freeing it. + * + * Returns length of result on success, -ve on error. */ int dns_resolve_server_name_to_ip(const char *unc, char **ip_addr) { - const struct cred *saved_cred; - int rc = -EAGAIN; - struct key *rkey = ERR_PTR(-EAGAIN); + struct sockaddr_storage ss; + const char *hostname, *sep; char *name; - char *data = NULL; - int len; + int len, rc; if (!ip_addr || !unc) return -EINVAL; - /* search for server name delimiter */ len = strlen(unc); if (len < 3) { cFYI(1, "%s: unc is too short: %s", __func__, unc); return -EINVAL; } - len -= 2; - name = memchr(unc+2, '\\', len); - if (!name) { - cFYI(1, "%s: probably server name is whole unc: %s", - __func__, unc); - } else { - len = (name - unc) - 2/* leading // */; - } - - name = kmalloc(len+1, GFP_KERNEL); - if (!name) { - rc = -ENOMEM; - return rc; - } - memcpy(name, unc+2, len); - name[len] = 0; - - if (is_ip(name)) { - cFYI(1, "%s: it is IP, skipping dns upcall: %s", - __func__, name); - data = name; - goto skip_upcall; - } - saved_cred = override_creds(dns_resolver_cache); - rkey = request_key(&key_type_dns_resolver, name, ""); - revert_creds(saved_cred); - if (!IS_ERR(rkey)) { - if (!(rkey->perm & KEY_USR_VIEW)) { - down_read(&rkey->sem); - rkey->perm |= KEY_USR_VIEW; - up_read(&rkey->sem); - } - len = rkey->type_data.x[0]; - data = rkey->payload.data; - } else { - cERROR(1, "%s: unable to resolve: %s", __func__, name); - goto out; - } - -skip_upcall: - if (data) { - *ip_addr = kmalloc(len + 1, GFP_KERNEL); - if (*ip_addr) { - memcpy(*ip_addr, data, len + 1); - if (!IS_ERR(rkey)) - cFYI(1, "%s: resolved: %s to %s", __func__, - name, - *ip_addr - ); - rc = 0; - } else { - rc = -ENOMEM; - } - if (!IS_ERR(rkey)) - key_put(rkey); - } + /* Discount leading slashes for cifs */ + len -= 2; + hostname = unc + 2; -out: - kfree(name); + /* Search for server name delimiter */ + sep = memchr(hostname, '\\', len); + if (sep) + len = sep - unc; + else + cFYI(1, "%s: probably server name is whole unc: %s", + __func__, unc); + + /* Try to interpret hostname as an IPv4 or IPv6 address */ + rc = cifs_convert_address((struct sockaddr *)&ss, hostname, len); + if (rc > 0) + goto name_is_IP_address; + + /* Perform the upcall */ + rc = dns_query(NULL, hostname, len, NULL, ip_addr, NULL); + if (rc < 0) + cERROR(1, "%s: unable to resolve: %*.*s", + __func__, len, len, hostname); + else + cFYI(1, "%s: resolved: %*.*s to %s", + __func__, len, len, hostname, *ip_addr); return rc; -} -int __init cifs_init_dns_resolver(void) -{ - struct cred *cred; - struct key *keyring; - int ret; - - printk(KERN_NOTICE "Registering the %s key type\n", - key_type_dns_resolver.name); - - /* create an override credential set with a special thread keyring in - * which DNS requests are cached - * - * this is used to prevent malicious redirections from being installed - * with add_key(). - */ - cred = prepare_kernel_cred(NULL); - if (!cred) +name_is_IP_address: + name = kmalloc(len + 1, GFP_KERNEL); + if (!name) return -ENOMEM; - - keyring = key_alloc(&key_type_keyring, ".dns_resolver", 0, 0, cred, - (KEY_POS_ALL & ~KEY_POS_SETATTR) | - KEY_USR_VIEW | KEY_USR_READ, - KEY_ALLOC_NOT_IN_QUOTA); - if (IS_ERR(keyring)) { - ret = PTR_ERR(keyring); - goto failed_put_cred; - } - - ret = key_instantiate_and_link(keyring, NULL, 0, NULL, NULL); - if (ret < 0) - goto failed_put_key; - - ret = register_key_type(&key_type_dns_resolver); - if (ret < 0) - goto failed_put_key; - - /* instruct request_key() to use this special keyring as a cache for - * the results it looks up */ - cred->thread_keyring = keyring; - cred->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING; - dns_resolver_cache = cred; + memcpy(name, hostname, len); + name[len] = 0; + cFYI(1, "%s: unc is IP, skipping dns upcall: %s", __func__, name); + *ip_addr = name; return 0; - -failed_put_key: - key_put(keyring); -failed_put_cred: - put_cred(cred); - return ret; -} - -void cifs_exit_dns_resolver(void) -{ - key_revoke(dns_resolver_cache->thread_keyring); - unregister_key_type(&key_type_dns_resolver); - put_cred(dns_resolver_cache); - printk(KERN_NOTICE "Unregistered %s key type\n", - key_type_dns_resolver.name); } diff --git a/fs/cifs/dns_resolve.h b/fs/cifs/dns_resolve.h index 5d7f291df162..d3f5d27f4d06 100644 --- a/fs/cifs/dns_resolve.h +++ b/fs/cifs/dns_resolve.h @@ -24,8 +24,6 @@ #define _DNS_RESOLVE_H #ifdef __KERNEL__ -extern int __init cifs_init_dns_resolver(void); -extern void cifs_exit_dns_resolver(void); extern int dns_resolve_server_name_to_ip(const char *unc, char **ip_addr); #endif /* KERNEL */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index fa04a00d126d..db11fdef0e92 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2307,8 +2307,7 @@ static void cifs_invalidate_page(struct page *page, unsigned long offset) cifs_fscache_invalidate_page(page, &cifsi->vfs_inode); } -static void -cifs_oplock_break(struct slow_work *work) +void cifs_oplock_break(struct work_struct *work) { struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo, oplock_break); @@ -2345,33 +2344,30 @@ cifs_oplock_break(struct slow_work *work) LOCKING_ANDX_OPLOCK_RELEASE, false); cFYI(1, "Oplock release rc = %d", rc); } + + /* + * We might have kicked in before is_valid_oplock_break() + * finished grabbing reference for us. Make sure it's done by + * waiting for GlobalSMSSeslock. + */ + write_lock(&GlobalSMBSeslock); + write_unlock(&GlobalSMBSeslock); + + cifs_oplock_break_put(cfile); } -static int -cifs_oplock_break_get(struct slow_work *work) +void cifs_oplock_break_get(struct cifsFileInfo *cfile) { - struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo, - oplock_break); mntget(cfile->mnt); cifsFileInfo_get(cfile); - return 0; } -static void -cifs_oplock_break_put(struct slow_work *work) +void cifs_oplock_break_put(struct cifsFileInfo *cfile) { - struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo, - oplock_break); mntput(cfile->mnt); cifsFileInfo_put(cfile); } -const struct slow_work_ops cifs_oplock_break_ops = { - .get_ref = cifs_oplock_break_get, - .put_ref = cifs_oplock_break_put, - .execute = cifs_oplock_break, -}; - const struct address_space_operations cifs_addr_ops = { .readpage = cifs_readpage, .readpages = cifs_readpages, diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index a15b3a9bbff4..dc4c47ab9588 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -732,15 +732,9 @@ cifs_find_inode(struct inode *inode, void *opaque) if ((inode->i_mode & S_IFMT) != (fattr->cf_mode & S_IFMT)) return 0; - /* - * uh oh -- it's a directory. We can't use it since hardlinked dirs are - * verboten. Disable serverino and return it as if it were found, the - * caller can discard it, generate a uniqueid and retry the find - */ - if (S_ISDIR(inode->i_mode) && !list_empty(&inode->i_dentry)) { + /* if it's not a directory or has no dentries, then flag it */ + if (S_ISDIR(inode->i_mode) && !list_empty(&inode->i_dentry)) fattr->cf_flags |= CIFS_FATTR_INO_COLLISION; - cifs_autodisable_serverino(CIFS_SB(inode->i_sb)); - } return 1; } @@ -754,6 +748,27 @@ cifs_init_inode(struct inode *inode, void *opaque) return 0; } +/* + * walk dentry list for an inode and report whether it has aliases that + * are hashed. We use this to determine if a directory inode can actually + * be used. + */ +static bool +inode_has_hashed_dentries(struct inode *inode) +{ + struct dentry *dentry; + + spin_lock(&dcache_lock); + list_for_each_entry(dentry, &inode->i_dentry, d_alias) { + if (!d_unhashed(dentry) || IS_ROOT(dentry)) { + spin_unlock(&dcache_lock); + return true; + } + } + spin_unlock(&dcache_lock); + return false; +} + /* Given fattrs, get a corresponding inode */ struct inode * cifs_iget(struct super_block *sb, struct cifs_fattr *fattr) @@ -769,12 +784,16 @@ retry_iget5_locked: inode = iget5_locked(sb, hash, cifs_find_inode, cifs_init_inode, fattr); if (inode) { - /* was there a problematic inode number collision? */ + /* was there a potentially problematic inode collision? */ if (fattr->cf_flags & CIFS_FATTR_INO_COLLISION) { - iput(inode); - fattr->cf_uniqueid = iunique(sb, ROOT_I); fattr->cf_flags &= ~CIFS_FATTR_INO_COLLISION; - goto retry_iget5_locked; + + if (inode_has_hashed_dentries(inode)) { + cifs_autodisable_serverino(CIFS_SB(sb)); + iput(inode); + fattr->cf_uniqueid = iunique(sb, ROOT_I); + goto retry_iget5_locked; + } } cifs_fattr_to_inode(inode, fattr); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 1394aa37f26c..3ccadc1326d6 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -498,7 +498,6 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv) struct cifsTconInfo *tcon; struct cifsInodeInfo *pCifsInode; struct cifsFileInfo *netfile; - int rc; cFYI(1, "Checking for oplock break or dnotify response"); if ((pSMB->hdr.Command == SMB_COM_NT_TRANSACT) && @@ -583,13 +582,18 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv) pCifsInode->clientCanCacheAll = false; if (pSMB->OplockLevel == 0) pCifsInode->clientCanCacheRead = false; - rc = slow_work_enqueue(&netfile->oplock_break); - if (rc) { - cERROR(1, "failed to enqueue oplock " - "break: %d\n", rc); - } else { - netfile->oplock_break_cancelled = false; - } + + /* + * cifs_oplock_break_put() can't be called + * from here. Get reference after queueing + * succeeded. cifs_oplock_break() will + * synchronize using GlobalSMSSeslock. + */ + if (queue_work(system_nrt_wq, + &netfile->oplock_break)) + cifs_oplock_break_get(netfile); + netfile->oplock_break_cancelled = false; + read_unlock(&GlobalSMBSeslock); read_unlock(&cifs_tcp_ses_lock); return true; diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index c6721ee26dbc..f97851119e6c 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -140,17 +140,18 @@ static const struct smb_to_posix_error mapping_table_ERRHRD[] = { * Returns 0 on failure. */ static int -cifs_inet_pton(const int address_family, const char *cp, void *dst) +cifs_inet_pton(const int address_family, const char *cp, int len, void *dst) { int ret = 0; /* calculate length by finding first slash or NULL */ if (address_family == AF_INET) - ret = in4_pton(cp, -1 /* len */, dst, '\\', NULL); + ret = in4_pton(cp, len, dst, '\\', NULL); else if (address_family == AF_INET6) - ret = in6_pton(cp, -1 /* len */, dst , '\\', NULL); + ret = in6_pton(cp, len, dst , '\\', NULL); - cFYI(DBG2, "address conversion returned %d for %s", ret, cp); + cFYI(DBG2, "address conversion returned %d for %*.*s", + ret, len, len, cp); if (ret > 0) ret = 1; return ret; @@ -165,37 +166,39 @@ cifs_inet_pton(const int address_family, const char *cp, void *dst) * Returns 0 on failure. */ int -cifs_convert_address(struct sockaddr *dst, char *src) +cifs_convert_address(struct sockaddr *dst, const char *src, int len) { - int rc; - char *pct, *endp; + int rc, alen, slen; + const char *pct; + char *endp, scope_id[13]; struct sockaddr_in *s4 = (struct sockaddr_in *) dst; struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) dst; /* IPv4 address */ - if (cifs_inet_pton(AF_INET, src, &s4->sin_addr.s_addr)) { + if (cifs_inet_pton(AF_INET, src, len, &s4->sin_addr.s_addr)) { s4->sin_family = AF_INET; return 1; } - /* temporarily terminate string */ - pct = strchr(src, '%'); - if (pct) - *pct = '\0'; - - rc = cifs_inet_pton(AF_INET6, src, &s6->sin6_addr.s6_addr); - - /* repair temp termination (if any) and make pct point to scopeid */ - if (pct) - *pct++ = '%'; + /* attempt to exclude the scope ID from the address part */ + pct = memchr(src, '%', len); + alen = pct ? pct - src : len; + rc = cifs_inet_pton(AF_INET6, src, alen, &s6->sin6_addr.s6_addr); if (!rc) return rc; s6->sin6_family = AF_INET6; if (pct) { + /* grab the scope ID */ + slen = len - (alen + 1); + if (slen <= 0 || slen > 12) + return 0; + memcpy(scope_id, pct + 1, slen); + scope_id[slen] = '\0'; + s6->sin6_scope_id = (u32) simple_strtoul(pct, &endp, 0); - if (!*pct || *endp) + if (endp != scope_id + slen) return 0; } @@ -203,10 +206,10 @@ cifs_convert_address(struct sockaddr *dst, char *src) } int -cifs_fill_sockaddr(struct sockaddr *dst, char *src, +cifs_fill_sockaddr(struct sockaddr *dst, const char *src, int len, const unsigned short int port) { - if (!cifs_convert_address(dst, src)) + if (!cifs_convert_address(dst, src, len)) return 0; switch (dst->sa_family) { diff --git a/fs/exec.c b/fs/exec.c index e19de6a80339..97d91a03fb13 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -653,6 +653,7 @@ int setup_arg_pages(struct linux_binprm *bprm, else stack_base = vma->vm_start - stack_expand; #endif + current->mm->start_stack = bprm->p; ret = expand_stack(vma, stack_base); if (ret) ret = -EFAULT; diff --git a/fs/file.c b/fs/file.c index 34bb7f71d994..cccaead962c2 100644 --- a/fs/file.c +++ b/fs/file.c @@ -178,7 +178,6 @@ static struct fdtable * alloc_fdtable(unsigned int nr) fdt->open_fds = (fd_set *)data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = (fd_set *)data; - INIT_RCU_HEAD(&fdt->rcu); fdt->next = NULL; return fdt; @@ -312,7 +311,6 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp) new_fdt->close_on_exec = (fd_set *)&newf->close_on_exec_init; new_fdt->open_fds = (fd_set *)&newf->open_fds_init; new_fdt->fd = &newf->fd_array[0]; - INIT_RCU_HEAD(&new_fdt->rcu); new_fdt->next = NULL; spin_lock(&oldf->file_lock); @@ -430,7 +428,6 @@ struct files_struct init_files = { .fd = &init_files.fd_array[0], .close_on_exec = (fd_set *)&init_files.close_on_exec_init, .open_fds = (fd_set *)&init_files.open_fds_init, - .rcu = RCU_HEAD_INIT, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_task.file_lock), }; diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig index cc94bb9563f2..3f6dfa989881 100644 --- a/fs/fscache/Kconfig +++ b/fs/fscache/Kconfig @@ -1,7 +1,6 @@ config FSCACHE tristate "General filesystem local caching manager" - select SLOW_WORK help This option enables a generic filesystem caching manager that can be used by various network and other filesystems to cache data locally. diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index edd7434ab6e5..6a026441c5a6 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -82,6 +82,14 @@ extern unsigned fscache_defer_lookup; extern unsigned fscache_defer_create; extern unsigned fscache_debug; extern struct kobject *fscache_root; +extern struct workqueue_struct *fscache_object_wq; +extern struct workqueue_struct *fscache_op_wq; +DECLARE_PER_CPU(wait_queue_head_t, fscache_object_cong_wait); + +static inline bool fscache_object_congested(void) +{ + return workqueue_congested(WORK_CPU_UNBOUND, fscache_object_wq); +} extern int fscache_wait_bit(void *); extern int fscache_wait_bit_interruptible(void *); diff --git a/fs/fscache/main.c b/fs/fscache/main.c index add6bdb53f04..f9d856773f79 100644 --- a/fs/fscache/main.c +++ b/fs/fscache/main.c @@ -15,6 +15,7 @@ #include <linux/sched.h> #include <linux/completion.h> #include <linux/slab.h> +#include <linux/seq_file.h> #include "internal.h" MODULE_DESCRIPTION("FS Cache Manager"); @@ -40,22 +41,105 @@ MODULE_PARM_DESC(fscache_debug, "FS-Cache debugging mask"); struct kobject *fscache_root; +struct workqueue_struct *fscache_object_wq; +struct workqueue_struct *fscache_op_wq; + +DEFINE_PER_CPU(wait_queue_head_t, fscache_object_cong_wait); + +/* these values serve as lower bounds, will be adjusted in fscache_init() */ +static unsigned fscache_object_max_active = 4; +static unsigned fscache_op_max_active = 2; + +#ifdef CONFIG_SYSCTL +static struct ctl_table_header *fscache_sysctl_header; + +static int fscache_max_active_sysctl(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + struct workqueue_struct **wqp = table->extra1; + unsigned int *datap = table->data; + int ret; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); + if (ret == 0) + workqueue_set_max_active(*wqp, *datap); + return ret; +} + +ctl_table fscache_sysctls[] = { + { + .procname = "object_max_active", + .data = &fscache_object_max_active, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = fscache_max_active_sysctl, + .extra1 = &fscache_object_wq, + }, + { + .procname = "operation_max_active", + .data = &fscache_op_max_active, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = fscache_max_active_sysctl, + .extra1 = &fscache_op_wq, + }, + {} +}; + +ctl_table fscache_sysctls_root[] = { + { + .procname = "fscache", + .mode = 0555, + .child = fscache_sysctls, + }, + {} +}; +#endif /* * initialise the fs caching module */ static int __init fscache_init(void) { + unsigned int nr_cpus = num_possible_cpus(); + unsigned int cpu; int ret; - ret = slow_work_register_user(THIS_MODULE); - if (ret < 0) - goto error_slow_work; + fscache_object_max_active = + clamp_val(nr_cpus, + fscache_object_max_active, WQ_UNBOUND_MAX_ACTIVE); + + ret = -ENOMEM; + fscache_object_wq = alloc_workqueue("fscache_object", WQ_UNBOUND, + fscache_object_max_active); + if (!fscache_object_wq) + goto error_object_wq; + + fscache_op_max_active = + clamp_val(fscache_object_max_active / 2, + fscache_op_max_active, WQ_UNBOUND_MAX_ACTIVE); + + ret = -ENOMEM; + fscache_op_wq = alloc_workqueue("fscache_operation", WQ_UNBOUND, + fscache_op_max_active); + if (!fscache_op_wq) + goto error_op_wq; + + for_each_possible_cpu(cpu) + init_waitqueue_head(&per_cpu(fscache_object_cong_wait, cpu)); ret = fscache_proc_init(); if (ret < 0) goto error_proc; +#ifdef CONFIG_SYSCTL + ret = -ENOMEM; + fscache_sysctl_header = register_sysctl_table(fscache_sysctls_root); + if (!fscache_sysctl_header) + goto error_sysctl; +#endif + fscache_cookie_jar = kmem_cache_create("fscache_cookie_jar", sizeof(struct fscache_cookie), 0, @@ -78,10 +162,16 @@ static int __init fscache_init(void) error_kobj: kmem_cache_destroy(fscache_cookie_jar); error_cookie_jar: +#ifdef CONFIG_SYSCTL + unregister_sysctl_table(fscache_sysctl_header); +error_sysctl: +#endif fscache_proc_cleanup(); error_proc: - slow_work_unregister_user(THIS_MODULE); -error_slow_work: + destroy_workqueue(fscache_op_wq); +error_op_wq: + destroy_workqueue(fscache_object_wq); +error_object_wq: return ret; } @@ -96,8 +186,12 @@ static void __exit fscache_exit(void) kobject_put(fscache_root); kmem_cache_destroy(fscache_cookie_jar); +#ifdef CONFIG_SYSCTL + unregister_sysctl_table(fscache_sysctl_header); +#endif fscache_proc_cleanup(); - slow_work_unregister_user(THIS_MODULE); + destroy_workqueue(fscache_op_wq); + destroy_workqueue(fscache_object_wq); printk(KERN_NOTICE "FS-Cache: Unloaded\n"); } diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c index 4a8eb31c5338..ebe29c581380 100644 --- a/fs/fscache/object-list.c +++ b/fs/fscache/object-list.c @@ -34,8 +34,8 @@ struct fscache_objlist_data { #define FSCACHE_OBJLIST_CONFIG_NOREADS 0x00000200 /* show objects without active reads */ #define FSCACHE_OBJLIST_CONFIG_EVENTS 0x00000400 /* show objects with events */ #define FSCACHE_OBJLIST_CONFIG_NOEVENTS 0x00000800 /* show objects without no events */ -#define FSCACHE_OBJLIST_CONFIG_WORK 0x00001000 /* show objects with slow work */ -#define FSCACHE_OBJLIST_CONFIG_NOWORK 0x00002000 /* show objects without slow work */ +#define FSCACHE_OBJLIST_CONFIG_WORK 0x00001000 /* show objects with work */ +#define FSCACHE_OBJLIST_CONFIG_NOWORK 0x00002000 /* show objects without work */ u8 buf[512]; /* key and aux data buffer */ }; @@ -231,12 +231,11 @@ static int fscache_objlist_show(struct seq_file *m, void *v) READS, NOREADS); FILTER(obj->events & obj->event_mask, EVENTS, NOEVENTS); - FILTER(obj->work.flags & ~(1UL << SLOW_WORK_VERY_SLOW), - WORK, NOWORK); + FILTER(work_busy(&obj->work), WORK, NOWORK); } seq_printf(m, - "%8x %8x %s %5u %3u %3u %3u %2u %5u %2lx %2lx %1lx %1lx | ", + "%8x %8x %s %5u %3u %3u %3u %2u %5u %2lx %2lx %1lx %1x | ", obj->debug_id, obj->parent ? obj->parent->debug_id : -1, fscache_object_states_short[obj->state], @@ -249,7 +248,7 @@ static int fscache_objlist_show(struct seq_file *m, void *v) obj->event_mask & FSCACHE_OBJECT_EVENTS_MASK, obj->events, obj->flags, - obj->work.flags); + work_busy(&obj->work)); no_cookie = true; keylen = auxlen = 0; diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 0b589a9b4ffc..b6b897c550ac 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -14,7 +14,6 @@ #define FSCACHE_DEBUG_LEVEL COOKIE #include <linux/module.h> -#include <linux/seq_file.h> #include "internal.h" const char *fscache_object_states[FSCACHE_OBJECT__NSTATES] = { @@ -50,12 +49,8 @@ const char fscache_object_states_short[FSCACHE_OBJECT__NSTATES][5] = { [FSCACHE_OBJECT_DEAD] = "DEAD", }; -static void fscache_object_slow_work_put_ref(struct slow_work *); -static int fscache_object_slow_work_get_ref(struct slow_work *); -static void fscache_object_slow_work_execute(struct slow_work *); -#ifdef CONFIG_SLOW_WORK_DEBUG -static void fscache_object_slow_work_desc(struct slow_work *, struct seq_file *); -#endif +static int fscache_get_object(struct fscache_object *); +static void fscache_put_object(struct fscache_object *); static void fscache_initialise_object(struct fscache_object *); static void fscache_lookup_object(struct fscache_object *); static void fscache_object_available(struct fscache_object *); @@ -64,17 +59,6 @@ static void fscache_withdraw_object(struct fscache_object *); static void fscache_enqueue_dependents(struct fscache_object *); static void fscache_dequeue_object(struct fscache_object *); -const struct slow_work_ops fscache_object_slow_work_ops = { - .owner = THIS_MODULE, - .get_ref = fscache_object_slow_work_get_ref, - .put_ref = fscache_object_slow_work_put_ref, - .execute = fscache_object_slow_work_execute, -#ifdef CONFIG_SLOW_WORK_DEBUG - .desc = fscache_object_slow_work_desc, -#endif -}; -EXPORT_SYMBOL(fscache_object_slow_work_ops); - /* * we need to notify the parent when an op completes that we had outstanding * upon it @@ -345,7 +329,7 @@ unsupported_event: /* * execute an object */ -static void fscache_object_slow_work_execute(struct slow_work *work) +void fscache_object_work_func(struct work_struct *work) { struct fscache_object *object = container_of(work, struct fscache_object, work); @@ -359,23 +343,9 @@ static void fscache_object_slow_work_execute(struct slow_work *work) if (object->events & object->event_mask) fscache_enqueue_object(object); clear_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events); + fscache_put_object(object); } - -/* - * describe an object for slow-work debugging - */ -#ifdef CONFIG_SLOW_WORK_DEBUG -static void fscache_object_slow_work_desc(struct slow_work *work, - struct seq_file *m) -{ - struct fscache_object *object = - container_of(work, struct fscache_object, work); - - seq_printf(m, "FSC: OBJ%x: %s", - object->debug_id, - fscache_object_states_short[object->state]); -} -#endif +EXPORT_SYMBOL(fscache_object_work_func); /* * initialise an object @@ -393,7 +363,6 @@ static void fscache_initialise_object(struct fscache_object *object) _enter(""); ASSERT(object->cookie != NULL); ASSERT(object->cookie->parent != NULL); - ASSERT(list_empty(&object->work.link)); if (object->events & ((1 << FSCACHE_OBJECT_EV_ERROR) | (1 << FSCACHE_OBJECT_EV_RELEASE) | @@ -671,10 +640,8 @@ static void fscache_drop_object(struct fscache_object *object) object->parent = NULL; } - /* this just shifts the object release to the slow work processor */ - fscache_stat(&fscache_n_cop_put_object); - object->cache->ops->put_object(object); - fscache_stat_d(&fscache_n_cop_put_object); + /* this just shifts the object release to the work processor */ + fscache_put_object(object); _leave(""); } @@ -758,12 +725,10 @@ void fscache_withdrawing_object(struct fscache_cache *cache, } /* - * allow the slow work item processor to get a ref on an object + * get a ref on an object */ -static int fscache_object_slow_work_get_ref(struct slow_work *work) +static int fscache_get_object(struct fscache_object *object) { - struct fscache_object *object = - container_of(work, struct fscache_object, work); int ret; fscache_stat(&fscache_n_cop_grab_object); @@ -773,13 +738,10 @@ static int fscache_object_slow_work_get_ref(struct slow_work *work) } /* - * allow the slow work item processor to discard a ref on a work item + * discard a ref on a work item */ -static void fscache_object_slow_work_put_ref(struct slow_work *work) +static void fscache_put_object(struct fscache_object *object) { - struct fscache_object *object = - container_of(work, struct fscache_object, work); - fscache_stat(&fscache_n_cop_put_object); object->cache->ops->put_object(object); fscache_stat_d(&fscache_n_cop_put_object); @@ -792,8 +754,48 @@ void fscache_enqueue_object(struct fscache_object *object) { _enter("{OBJ%x}", object->debug_id); - slow_work_enqueue(&object->work); + if (fscache_get_object(object) >= 0) { + wait_queue_head_t *cong_wq = + &get_cpu_var(fscache_object_cong_wait); + + if (queue_work(fscache_object_wq, &object->work)) { + if (fscache_object_congested()) + wake_up(cong_wq); + } else + fscache_put_object(object); + + put_cpu_var(fscache_object_cong_wait); + } +} + +/** + * fscache_object_sleep_till_congested - Sleep until object wq is congested + * @timoutp: Scheduler sleep timeout + * + * Allow an object handler to sleep until the object workqueue is congested. + * + * The caller must set up a wake up event before calling this and must have set + * the appropriate sleep mode (such as TASK_UNINTERRUPTIBLE) and tested its own + * condition before calling this function as no test is made here. + * + * %true is returned if the object wq is congested, %false otherwise. + */ +bool fscache_object_sleep_till_congested(signed long *timeoutp) +{ + wait_queue_head_t *cong_wq = &__get_cpu_var(fscache_object_cong_wait); + DEFINE_WAIT(wait); + + if (fscache_object_congested()) + return true; + + add_wait_queue_exclusive(cong_wq, &wait); + if (!fscache_object_congested()) + *timeoutp = schedule_timeout(*timeoutp); + finish_wait(cong_wq, &wait); + + return fscache_object_congested(); } +EXPORT_SYMBOL_GPL(fscache_object_sleep_till_congested); /* * enqueue the dependents of an object for metadata-type processing @@ -819,9 +821,7 @@ static void fscache_enqueue_dependents(struct fscache_object *object) /* sort onto appropriate lists */ fscache_enqueue_object(dep); - fscache_stat(&fscache_n_cop_put_object); - dep->cache->ops->put_object(dep); - fscache_stat_d(&fscache_n_cop_put_object); + fscache_put_object(dep); if (!list_empty(&object->dependents)) cond_resched_lock(&object->lock); diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c index f17cecafae44..b9f34eaede09 100644 --- a/fs/fscache/operation.c +++ b/fs/fscache/operation.c @@ -42,16 +42,12 @@ void fscache_enqueue_operation(struct fscache_operation *op) fscache_stat(&fscache_n_op_enqueue); switch (op->flags & FSCACHE_OP_TYPE) { - case FSCACHE_OP_FAST: - _debug("queue fast"); + case FSCACHE_OP_ASYNC: + _debug("queue async"); atomic_inc(&op->usage); - if (!schedule_work(&op->fast_work)) + if (!queue_work(fscache_op_wq, &op->work)) fscache_put_operation(op); break; - case FSCACHE_OP_SLOW: - _debug("queue slow"); - slow_work_enqueue(&op->slow_work); - break; case FSCACHE_OP_MYTHREAD: _debug("queue for caller's attention"); break; @@ -455,36 +451,13 @@ void fscache_operation_gc(struct work_struct *work) } /* - * allow the slow work item processor to get a ref on an operation - */ -static int fscache_op_get_ref(struct slow_work *work) -{ - struct fscache_operation *op = - container_of(work, struct fscache_operation, slow_work); - - atomic_inc(&op->usage); - return 0; -} - -/* - * allow the slow work item processor to discard a ref on an operation - */ -static void fscache_op_put_ref(struct slow_work *work) -{ - struct fscache_operation *op = - container_of(work, struct fscache_operation, slow_work); - - fscache_put_operation(op); -} - -/* - * execute an operation using the slow thread pool to provide processing context - * - the caller holds a ref to this object, so we don't need to hold one + * execute an operation using fs_op_wq to provide processing context - + * the caller holds a ref to this object, so we don't need to hold one */ -static void fscache_op_execute(struct slow_work *work) +void fscache_op_work_func(struct work_struct *work) { struct fscache_operation *op = - container_of(work, struct fscache_operation, slow_work); + container_of(work, struct fscache_operation, work); unsigned long start; _enter("{OBJ%x OP%x,%d}", @@ -494,31 +467,7 @@ static void fscache_op_execute(struct slow_work *work) start = jiffies; op->processor(op); fscache_hist(fscache_ops_histogram, start); + fscache_put_operation(op); _leave(""); } - -/* - * describe an operation for slow-work debugging - */ -#ifdef CONFIG_SLOW_WORK_DEBUG -static void fscache_op_desc(struct slow_work *work, struct seq_file *m) -{ - struct fscache_operation *op = - container_of(work, struct fscache_operation, slow_work); - - seq_printf(m, "FSC: OBJ%x OP%x: %s/%s fl=%lx", - op->object->debug_id, op->debug_id, - op->name, op->state, op->flags); -} -#endif - -const struct slow_work_ops fscache_op_slow_work_ops = { - .owner = THIS_MODULE, - .get_ref = fscache_op_get_ref, - .put_ref = fscache_op_put_ref, - .execute = fscache_op_execute, -#ifdef CONFIG_SLOW_WORK_DEBUG - .desc = fscache_op_desc, -#endif -}; diff --git a/fs/fscache/page.c b/fs/fscache/page.c index 723b889fd219..41c441c2058d 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -105,7 +105,7 @@ bool __fscache_maybe_release_page(struct fscache_cookie *cookie, page_busy: /* we might want to wait here, but that could deadlock the allocator as - * the slow-work threads writing to the cache may all end up sleeping + * the work threads writing to the cache may all end up sleeping * on memory allocation */ fscache_stat(&fscache_n_store_vmscan_busy); return false; @@ -188,9 +188,8 @@ int __fscache_attr_changed(struct fscache_cookie *cookie) return -ENOMEM; } - fscache_operation_init(op, NULL); - fscache_operation_init_slow(op, fscache_attr_changed_op); - op->flags = FSCACHE_OP_SLOW | (1 << FSCACHE_OP_EXCLUSIVE); + fscache_operation_init(op, fscache_attr_changed_op, NULL); + op->flags = FSCACHE_OP_ASYNC | (1 << FSCACHE_OP_EXCLUSIVE); fscache_set_op_name(op, "Attr"); spin_lock(&cookie->lock); @@ -218,24 +217,6 @@ nobufs: EXPORT_SYMBOL(__fscache_attr_changed); /* - * handle secondary execution given to a retrieval op on behalf of the - * cache - */ -static void fscache_retrieval_work(struct work_struct *work) -{ - struct fscache_retrieval *op = - container_of(work, struct fscache_retrieval, op.fast_work); - unsigned long start; - - _enter("{OP%x}", op->op.debug_id); - - start = jiffies; - op->op.processor(&op->op); - fscache_hist(fscache_ops_histogram, start); - fscache_put_operation(&op->op); -} - -/* * release a retrieval op reference */ static void fscache_release_retrieval_op(struct fscache_operation *_op) @@ -269,13 +250,12 @@ static struct fscache_retrieval *fscache_alloc_retrieval( return NULL; } - fscache_operation_init(&op->op, fscache_release_retrieval_op); + fscache_operation_init(&op->op, NULL, fscache_release_retrieval_op); op->op.flags = FSCACHE_OP_MYTHREAD | (1 << FSCACHE_OP_WAITING); op->mapping = mapping; op->end_io_func = end_io_func; op->context = context; op->start_time = jiffies; - INIT_WORK(&op->op.fast_work, fscache_retrieval_work); INIT_LIST_HEAD(&op->to_do); fscache_set_op_name(&op->op, "Retr"); return op; @@ -795,9 +775,9 @@ int __fscache_write_page(struct fscache_cookie *cookie, if (!op) goto nomem; - fscache_operation_init(&op->op, fscache_release_write_op); - fscache_operation_init_slow(&op->op, fscache_write_op); - op->op.flags = FSCACHE_OP_SLOW | (1 << FSCACHE_OP_WAITING); + fscache_operation_init(&op->op, fscache_write_op, + fscache_release_write_op); + op->op.flags = FSCACHE_OP_ASYNC | (1 << FSCACHE_OP_WAITING); fscache_set_op_name(&op->op, "Write1"); ret = radix_tree_preload(gfp & ~__GFP_HIGHMEM); @@ -852,7 +832,7 @@ int __fscache_write_page(struct fscache_cookie *cookie, fscache_stat(&fscache_n_store_ops); fscache_stat(&fscache_n_stores_ok); - /* the slow work queue now carries its own ref on the object */ + /* the work queue now carries its own ref on the object */ fscache_put_operation(&op->op); _leave(" = 0"); return 0; diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig index a47b43107112..cc9665522148 100644 --- a/fs/gfs2/Kconfig +++ b/fs/gfs2/Kconfig @@ -7,7 +7,6 @@ config GFS2_FS select IP_SCTP if DLM_SCTP select FS_POSIX_ACL select CRC32 - select SLOW_WORK select QUOTACTL help A cluster filesystem. diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 8fcbce48a128..fdbf4b366fa5 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -12,7 +12,6 @@ #include <linux/fs.h> #include <linux/workqueue.h> -#include <linux/slow-work.h> #include <linux/dlm.h> #include <linux/buffer_head.h> @@ -383,7 +382,7 @@ struct gfs2_journal_extent { struct gfs2_jdesc { struct list_head jd_list; struct list_head extent_list; - struct slow_work jd_work; + struct work_struct jd_work; struct inode *jd_inode; unsigned long jd_flags; #define JDF_RECOVERY 1 diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index fb2a5f93b7c3..b1e9630eb46a 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -15,7 +15,6 @@ #include <linux/init.h> #include <linux/gfs2_ondisk.h> #include <asm/atomic.h> -#include <linux/slow-work.h> #include "gfs2.h" #include "incore.h" @@ -24,6 +23,7 @@ #include "util.h" #include "glock.h" #include "quota.h" +#include "recovery.h" static struct shrinker qd_shrinker = { .shrink = gfs2_shrink_qd_memory, @@ -138,9 +138,11 @@ static int __init init_gfs2_fs(void) if (error) goto fail_unregister; - error = slow_work_register_user(THIS_MODULE); - if (error) - goto fail_slow; + error = -ENOMEM; + gfs_recovery_wq = alloc_workqueue("gfs_recovery", + WQ_NON_REENTRANT | WQ_RESCUER, 0); + if (!gfs_recovery_wq) + goto fail_wq; gfs2_register_debugfs(); @@ -148,7 +150,7 @@ static int __init init_gfs2_fs(void) return 0; -fail_slow: +fail_wq: unregister_filesystem(&gfs2meta_fs_type); fail_unregister: unregister_filesystem(&gfs2_fs_type); @@ -190,7 +192,7 @@ static void __exit exit_gfs2_fs(void) gfs2_unregister_debugfs(); unregister_filesystem(&gfs2_fs_type); unregister_filesystem(&gfs2meta_fs_type); - slow_work_unregister_user(THIS_MODULE); + destroy_workqueue(gfs_recovery_wq); kmem_cache_destroy(gfs2_quotad_cachep); kmem_cache_destroy(gfs2_rgrpd_cachep); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 45a4a36195d8..4f44bdeb2f03 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -17,7 +17,6 @@ #include <linux/namei.h> #include <linux/mount.h> #include <linux/gfs2_ondisk.h> -#include <linux/slow-work.h> #include <linux/quotaops.h> #include "gfs2.h" @@ -673,7 +672,7 @@ static int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh) break; INIT_LIST_HEAD(&jd->extent_list); - slow_work_init(&jd->jd_work, &gfs2_recover_ops); + INIT_WORK(&jd->jd_work, gfs2_recover_func); jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1); if (!jd->jd_inode || IS_ERR(jd->jd_inode)) { if (!jd->jd_inode) @@ -782,7 +781,8 @@ static int init_journal(struct gfs2_sbd *sdp, int undo) if (sdp->sd_lockstruct.ls_first) { unsigned int x; for (x = 0; x < sdp->sd_journals; x++) { - error = gfs2_recover_journal(gfs2_jdesc_find(sdp, x)); + error = gfs2_recover_journal(gfs2_jdesc_find(sdp, x), + true); if (error) { fs_err(sdp, "error recovering journal %u: %d\n", x, error); @@ -792,7 +792,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo) gfs2_others_may_mount(sdp); } else if (!sdp->sd_args.ar_spectator) { - error = gfs2_recover_journal(sdp->sd_jdesc); + error = gfs2_recover_journal(sdp->sd_jdesc, true); if (error) { fs_err(sdp, "error recovering my journal: %d\n", error); goto fail_jinode_gh; diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 4b9bece3d437..f7f89a94a5a4 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -14,7 +14,6 @@ #include <linux/buffer_head.h> #include <linux/gfs2_ondisk.h> #include <linux/crc32.h> -#include <linux/slow-work.h> #include "gfs2.h" #include "incore.h" @@ -28,6 +27,8 @@ #include "util.h" #include "dir.h" +struct workqueue_struct *gfs_recovery_wq; + int gfs2_replay_read_block(struct gfs2_jdesc *jd, unsigned int blk, struct buffer_head **bh) { @@ -443,23 +444,7 @@ static void gfs2_recovery_done(struct gfs2_sbd *sdp, unsigned int jid, kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp); } -static int gfs2_recover_get_ref(struct slow_work *work) -{ - struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work); - if (test_and_set_bit(JDF_RECOVERY, &jd->jd_flags)) - return -EBUSY; - return 0; -} - -static void gfs2_recover_put_ref(struct slow_work *work) -{ - struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work); - clear_bit(JDF_RECOVERY, &jd->jd_flags); - smp_mb__after_clear_bit(); - wake_up_bit(&jd->jd_flags, JDF_RECOVERY); -} - -static void gfs2_recover_work(struct slow_work *work) +void gfs2_recover_func(struct work_struct *work) { struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work); struct gfs2_inode *ip = GFS2_I(jd->jd_inode); @@ -578,7 +563,7 @@ static void gfs2_recover_work(struct slow_work *work) gfs2_glock_dq_uninit(&j_gh); fs_info(sdp, "jid=%u: Done\n", jd->jd_jid); - return; + goto done; fail_gunlock_tr: gfs2_glock_dq_uninit(&t_gh); @@ -590,32 +575,35 @@ fail_gunlock_j: } fs_info(sdp, "jid=%u: %s\n", jd->jd_jid, (error) ? "Failed" : "Done"); - fail: gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_GAVEUP); +done: + clear_bit(JDF_RECOVERY, &jd->jd_flags); + smp_mb__after_clear_bit(); + wake_up_bit(&jd->jd_flags, JDF_RECOVERY); } -struct slow_work_ops gfs2_recover_ops = { - .owner = THIS_MODULE, - .get_ref = gfs2_recover_get_ref, - .put_ref = gfs2_recover_put_ref, - .execute = gfs2_recover_work, -}; - - static int gfs2_recovery_wait(void *word) { schedule(); return 0; } -int gfs2_recover_journal(struct gfs2_jdesc *jd) +int gfs2_recover_journal(struct gfs2_jdesc *jd, bool wait) { int rv; - rv = slow_work_enqueue(&jd->jd_work); - if (rv) - return rv; - wait_on_bit(&jd->jd_flags, JDF_RECOVERY, gfs2_recovery_wait, TASK_UNINTERRUPTIBLE); + + if (test_and_set_bit(JDF_RECOVERY, &jd->jd_flags)) + return -EBUSY; + + /* we have JDF_RECOVERY, queue should always succeed */ + rv = queue_work(gfs_recovery_wq, &jd->jd_work); + BUG_ON(!rv); + + if (wait) + wait_on_bit(&jd->jd_flags, JDF_RECOVERY, gfs2_recovery_wait, + TASK_UNINTERRUPTIBLE); + return 0; } diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h index 1616ac22569a..2226136c7647 100644 --- a/fs/gfs2/recovery.h +++ b/fs/gfs2/recovery.h @@ -12,6 +12,8 @@ #include "incore.h" +extern struct workqueue_struct *gfs_recovery_wq; + static inline void gfs2_replay_incr_blk(struct gfs2_sbd *sdp, unsigned int *blk) { if (++*blk == sdp->sd_jdesc->jd_blocks) @@ -27,8 +29,8 @@ extern void gfs2_revoke_clean(struct gfs2_sbd *sdp); extern int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head); -extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd); -extern struct slow_work_ops gfs2_recover_ops; +extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd, bool wait); +extern void gfs2_recover_func(struct work_struct *work); #endif /* __RECOVERY_DOT_H__ */ diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index d019d0d55e00..ccacffd2faaa 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -25,6 +25,7 @@ #include "quota.h" #include "util.h" #include "glops.h" +#include "recovery.h" struct gfs2_attr { struct attribute attr; @@ -376,7 +377,7 @@ static ssize_t recover_store(struct gfs2_sbd *sdp, const char *buf, size_t len) list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) { if (jd->jd_jid != jid) continue; - rv = slow_work_enqueue(&jd->jd_work); + rv = gfs2_recover_journal(jd, false); break; } out: diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 5dcd4b0c5533..72c52656dc2e 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -459,7 +459,6 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, } /* everything is up and running, commence */ - INIT_RCU_HEAD(&p->rcu_head); rcu_assign_pointer(ptbl->part[partno], p); /* suppress uevent if the disk supresses it */ diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 1beaa739d0a6..1b27b5688f62 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -593,7 +593,8 @@ EXPORT_SYMBOL_GPL(sysfs_add_file_to_group); * @mode: file permissions. * */ -int sysfs_chmod_file(struct kobject *kobj, struct attribute *attr, mode_t mode) +int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr, + mode_t mode) { struct sysfs_dirent *sd; struct iattr newattrs; diff --git a/fs/udf/file.c b/fs/udf/file.c index 94e06d6bddbd..6e450e01a1bb 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -36,7 +36,6 @@ #include <linux/pagemap.h> #include <linux/buffer_head.h> #include <linux/aio.h> -#include <linux/smp_lock.h> #include "udf_i.h" #include "udf_sb.h" diff --git a/fs/udf/super.c b/fs/udf/super.c index 612d1e2e285a..12bb651e5400 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -1579,9 +1579,7 @@ static int udf_load_sequence(struct super_block *sb, struct buffer_head *bh, { struct anchorVolDescPtr *anchor; long main_s, main_e, reserve_s, reserve_e; - struct udf_sb_info *sbi; - sbi = UDF_SB(sb); anchor = (struct anchorVolDescPtr *)bh->b_data; /* Locate the main sequence */ |