diff options
Diffstat (limited to 'fs')
43 files changed, 499 insertions, 976 deletions
@@ -1734,6 +1734,18 @@ config SUNRPC config SUNRPC_GSS tristate +config SUNRPC_BIND34 + bool "Support for rpcbind versions 3 & 4 (EXPERIMENTAL)" + depends on SUNRPC && EXPERIMENTAL + help + Provides kernel support for querying rpcbind servers via versions 3 + and 4 of the rpcbind protocol. The kernel automatically falls back + to version 2 if a remote rpcbind service does not support versions + 3 or 4. + + If unsure, say N to get traditional behavior (version 2 rpcbind + requests only). + config RPCSEC_GSS_KRB5 tristate "Secure RPC: Kerberos V mechanism (EXPERIMENTAL)" depends on SUNRPC && EXPERIMENTAL @@ -2020,7 +2032,6 @@ config AFS_FS tristate "Andrew File System support (AFS) (EXPERIMENTAL)" depends on INET && EXPERIMENTAL select AF_RXRPC - select KEYS 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/Makefile b/fs/afs/Makefile index 01545eb..cf83e5d 100644 --- a/fs/afs/Makefile +++ b/fs/afs/Makefile @@ -18,7 +18,7 @@ kafs-objs := \ security.o \ server.o \ super.o \ - use-rtnetlink.o \ + netdevices.o \ vlclient.o \ vlocation.o \ vnode.o \ diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 639399f..9bdbf36 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -468,7 +468,7 @@ int __init afs_callback_update_init(void) /* * shut down the callback update process */ -void __exit afs_callback_update_kill(void) +void afs_callback_update_kill(void) { destroy_workqueue(afs_callback_update_worker); } diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 6685f4c..d5b2ad6 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -443,6 +443,7 @@ static void SRXAFSCB_GetCapabilities(struct work_struct *work) reply.ia.netmask[loop] = ifs[loop].netmask.s_addr; reply.ia.mtu[loop] = htonl(ifs[loop].mtu); } + kfree(ifs); } reply.cap.capcount = htonl(1); diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 2393d2a..e54e6c2 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -266,7 +266,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, call->unmarshall++; if (call->count < PAGE_SIZE) { - buffer = kmap_atomic(call->reply3, KM_USER0); + page = call->reply3; + buffer = kmap_atomic(page, KM_USER0); memset(buffer + PAGE_SIZE - call->count, 0, call->count); kunmap_atomic(buffer, KM_USER0); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 34665f7..d90c158 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -349,7 +349,6 @@ struct afs_permits { * record of one of a system's set of network interfaces */ struct afs_interface { - unsigned index; /* interface index */ struct in_addr address; /* IPv4 address bound to interface */ struct in_addr netmask; /* netmask applied to address */ unsigned mtu; /* MTU of interface */ @@ -392,7 +391,7 @@ extern void afs_give_up_callback(struct afs_vnode *); extern void afs_dispatch_give_up_callbacks(struct work_struct *); extern void afs_flush_callback_breaks(struct afs_server *); extern int __init afs_callback_update_init(void); -extern void __exit afs_callback_update_kill(void); +extern void afs_callback_update_kill(void); /* * cell.c @@ -564,7 +563,7 @@ extern void afs_fs_exit(void); * use-rtnetlink.c */ extern int afs_get_ipv4_interfaces(struct afs_interface *, size_t, bool); -extern int afs_get_MAC_address(u8 [6]); +extern int afs_get_MAC_address(u8 *, size_t); /* * vlclient.c @@ -591,7 +590,7 @@ extern struct afs_vlocation *afs_vlocation_lookup(struct afs_cell *, struct key *, const char *, size_t); extern void afs_put_vlocation(struct afs_vlocation *); -extern void __exit afs_vlocation_purge(void); +extern void afs_vlocation_purge(void); /* * vnode.c diff --git a/fs/afs/main.c b/fs/afs/main.c index 40c2704..80ec6fd 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -54,7 +54,7 @@ static int __init afs_get_client_UUID(void) /* read the MAC address of one of the external interfaces and construct * a UUID from it */ - ret = afs_get_MAC_address(afs_uuid.node); + ret = afs_get_MAC_address(afs_uuid.node, sizeof(afs_uuid.node)); if (ret < 0) return ret; diff --git a/fs/afs/netdevices.c b/fs/afs/netdevices.c new file mode 100644 index 0000000..fc27d4b --- /dev/null +++ b/fs/afs/netdevices.c @@ -0,0 +1,68 @@ +/* AFS network device helpers + * + * Copyright (c) 2007 Patrick McHardy <kaber@trash.net> + */ + +#include <linux/string.h> +#include <linux/rtnetlink.h> +#include <linux/inetdevice.h> +#include <linux/netdevice.h> +#include <linux/if_arp.h> +#include "internal.h" + +/* + * get a MAC address from a random ethernet interface that has a real one + * - the buffer will normally be 6 bytes in size + */ +int afs_get_MAC_address(u8 *mac, size_t maclen) +{ + struct net_device *dev; + int ret = -ENODEV; + + if (maclen != ETH_ALEN) + BUG(); + + rtnl_lock(); + dev = __dev_getfirstbyhwtype(ARPHRD_ETHER); + if (dev) { + memcpy(mac, dev->dev_addr, maclen); + ret = 0; + } + rtnl_unlock(); + return ret; +} + +/* + * get a list of this system's interface IPv4 addresses, netmasks and MTUs + * - maxbufs must be at least 1 + * - returns the number of interface records in the buffer + */ +int afs_get_ipv4_interfaces(struct afs_interface *bufs, size_t maxbufs, + bool wantloopback) +{ + struct net_device *dev; + struct in_device *idev; + int n = 0; + + ASSERT(maxbufs > 0); + + rtnl_lock(); + for_each_netdev(dev) { + if (dev->type == ARPHRD_LOOPBACK && !wantloopback) + continue; + idev = __in_dev_get_rtnl(dev); + if (!idev) + continue; + for_primary_ifa(idev) { + bufs[n].address.s_addr = ifa->ifa_address; + bufs[n].netmask.s_addr = ifa->ifa_mask; + bufs[n].mtu = dev->mtu; + n++; + if (n >= maxbufs) + goto out; + } endfor_ifa(idev); + } +out: + rtnl_unlock(); + return n; +} diff --git a/fs/afs/super.c b/fs/afs/super.c index cebd03c..41173f8 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -20,6 +20,7 @@ #include <linux/slab.h> #include <linux/fs.h> #include <linux/pagemap.h> +#include <linux/parser.h> #include "internal.h" #define AFS_FS_MAGIC 0x6B414653 /* 'kAFS' */ @@ -42,7 +43,7 @@ struct file_system_type afs_fs_type = { .name = "afs", .get_sb = afs_get_sb, .kill_sb = kill_anon_super, - .fs_flags = FS_BINARY_MOUNTDATA, + .fs_flags = 0, }; static const struct super_operations afs_super_ops = { @@ -58,6 +59,20 @@ static const struct super_operations afs_super_ops = { static struct kmem_cache *afs_inode_cachep; static atomic_t afs_count_active_inodes; +enum { + afs_no_opt, + afs_opt_cell, + afs_opt_rwpath, + afs_opt_vol, +}; + +static const match_table_t afs_options_list = { + { afs_opt_cell, "cell=%s" }, + { afs_opt_rwpath, "rwpath" }, + { afs_opt_vol, "vol=%s" }, + { afs_no_opt, NULL }, +}; + /* * initialise the filesystem */ @@ -115,31 +130,6 @@ void __exit afs_fs_exit(void) } /* - * check that an argument has a value - */ -static int want_arg(char **_value, const char *option) -{ - if (!_value || !*_value || !**_value) { - printk(KERN_NOTICE "kAFS: %s: argument missing\n", option); - return 0; - } - return 1; -} - -/* - * check that there's no subsequent value - */ -static int want_no_value(char *const *_value, const char *option) -{ - if (*_value && **_value) { - printk(KERN_NOTICE "kAFS: %s: Invalid argument: %s\n", - option, *_value); - return 0; - } - return 1; -} - -/* * parse the mount options * - this function has been shamelessly adapted from the ext3 fs which * shamelessly adapted it from the msdos fs @@ -148,48 +138,46 @@ static int afs_parse_options(struct afs_mount_params *params, char *options, const char **devname) { struct afs_cell *cell; - char *key, *value; - int ret; + substring_t args[MAX_OPT_ARGS]; + char *p; + int token; _enter("%s", options); options[PAGE_SIZE - 1] = 0; - ret = 0; - while ((key = strsep(&options, ","))) { - value = strchr(key, '='); - if (value) - *value++ = 0; - - _debug("kAFS: KEY: %s, VAL:%s", key, value ?: "-"); + while ((p = strsep(&options, ","))) { + if (!*p) + continue; - if (strcmp(key, "rwpath") == 0) { - if (!want_no_value(&value, "rwpath")) - return -EINVAL; - params->rwpath = 1; - } else if (strcmp(key, "vol") == 0) { - if (!want_arg(&value, "vol")) - return -EINVAL; - *devname = value; - } else if (strcmp(key, "cell") == 0) { - if (!want_arg(&value, "cell")) - return -EINVAL; - cell = afs_cell_lookup(value, strlen(value)); + token = match_token(p, afs_options_list, args); + switch (token) { + case afs_opt_cell: + cell = afs_cell_lookup(args[0].from, + args[0].to - args[0].from); if (IS_ERR(cell)) return PTR_ERR(cell); afs_put_cell(params->cell); params->cell = cell; - } else { - printk("kAFS: Unknown mount option: '%s'\n", key); - ret = -EINVAL; - goto error; + break; + + case afs_opt_rwpath: + params->rwpath = 1; + break; + + case afs_opt_vol: + *devname = args[0].from; + break; + + default: + printk(KERN_ERR "kAFS:" + " Unknown or invalid mount option: '%s'\n", p); + return -EINVAL; } } - ret = 0; -error: - _leave(" = %d", ret); - return ret; + _leave(" = 0"); + return 0; } /* @@ -361,7 +349,6 @@ error: /* * get an AFS superblock - * - TODO: don't use get_sb_nodev(), but rather call sget() directly */ static int afs_get_sb(struct file_system_type *fs_type, int flags, @@ -386,7 +373,6 @@ static int afs_get_sb(struct file_system_type *fs_type, goto error; } - ret = afs_parse_device_name(¶ms, dev_name); if (ret < 0) goto error; diff --git a/fs/afs/use-rtnetlink.c b/fs/afs/use-rtnetlink.c deleted file mode 100644 index f8991c7..0000000 --- a/fs/afs/use-rtnetlink.c +++ /dev/null @@ -1,473 +0,0 @@ -/* RTNETLINK client - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ -#include <linux/netlink.h> -#include <linux/rtnetlink.h> -#include <linux/if_addr.h> -#include <linux/if_arp.h> -#include <linux/inetdevice.h> -#include <net/netlink.h> -#include "internal.h" - -struct afs_rtm_desc { - struct socket *nlsock; - struct afs_interface *bufs; - u8 *mac; - size_t nbufs; - size_t maxbufs; - void *data; - ssize_t datalen; - size_t datamax; - int msg_seq; - unsigned mac_index; - bool wantloopback; - int (*parse)(struct afs_rtm_desc *, struct nlmsghdr *); -}; - -/* - * parse an RTM_GETADDR response - */ -static int afs_rtm_getaddr_parse(struct afs_rtm_desc *desc, - struct nlmsghdr *nlhdr) -{ - struct afs_interface *this; - struct ifaddrmsg *ifa; - struct rtattr *rtattr; - const char *name; - size_t len; - - ifa = (struct ifaddrmsg *) NLMSG_DATA(nlhdr); - - _enter("{ix=%d,af=%d}", ifa->ifa_index, ifa->ifa_family); - - if (ifa->ifa_family != AF_INET) { - _leave(" = 0 [family %d]", ifa->ifa_family); - return 0; - } - if (desc->nbufs >= desc->maxbufs) { - _leave(" = 0 [max %zu/%zu]", desc->nbufs, desc->maxbufs); - return 0; - } - - this = &desc->bufs[desc->nbufs]; - - this->index = ifa->ifa_index; - this->netmask.s_addr = inet_make_mask(ifa->ifa_prefixlen); - this->mtu = 0; - - rtattr = NLMSG_DATA(nlhdr) + NLMSG_ALIGN(sizeof(struct ifaddrmsg)); - len = NLMSG_PAYLOAD(nlhdr, sizeof(struct ifaddrmsg)); - - name = "unknown"; - for (; RTA_OK(rtattr, len); rtattr = RTA_NEXT(rtattr, len)) { - switch (rtattr->rta_type) { - case IFA_ADDRESS: - memcpy(&this->address, RTA_DATA(rtattr), 4); - break; - case IFA_LABEL: - name = RTA_DATA(rtattr); - break; - } - } - - _debug("%s: "NIPQUAD_FMT"/"NIPQUAD_FMT, - name, NIPQUAD(this->address), NIPQUAD(this->netmask)); - - desc->nbufs++; - _leave(" = 0"); - return 0; -} - -/* - * parse an RTM_GETLINK response for MTUs - */ -static int afs_rtm_getlink_if_parse(struct afs_rtm_desc *desc, - struct nlmsghdr *nlhdr) -{ - struct afs_interface *this; - struct ifinfomsg *ifi; - struct rtattr *rtattr; - const char *name; - size_t len, loop; - - ifi = (struct ifinfomsg *) NLMSG_DATA(nlhdr); - - _enter("{ix=%d}", ifi->ifi_index); - - for (loop = 0; loop < desc->nbufs; loop++) { - this = &desc->bufs[loop]; - if (this->index == ifi->ifi_index) - goto found; - } - - _leave(" = 0 [no match]"); - return 0; - -found: - if (ifi->ifi_type == ARPHRD_LOOPBACK && !desc->wantloopback) { - _leave(" = 0 [loopback]"); - return 0; - } - - rtattr = NLMSG_DATA(nlhdr) + NLMSG_ALIGN(sizeof(struct ifinfomsg)); - len = NLMSG_PAYLOAD(nlhdr, sizeof(struct ifinfomsg)); - - name = "unknown"; - for (; RTA_OK(rtattr, len); rtattr = RTA_NEXT(rtattr, len)) { - switch (rtattr->rta_type) { - case IFLA_MTU: - memcpy(&this->mtu, RTA_DATA(rtattr), 4); - break; - case IFLA_IFNAME: - name = RTA_DATA(rtattr); - break; - } - } - - _debug("%s: "NIPQUAD_FMT"/"NIPQUAD_FMT" mtu %u", - name, NIPQUAD(this->address), NIPQUAD(this->netmask), - this->mtu); - - _leave(" = 0"); - return 0; -} - -/* - * parse an RTM_GETLINK response for the MAC address belonging to the lowest - * non-internal interface - */ -static int afs_rtm_getlink_mac_parse(struct afs_rtm_desc *desc, - struct nlmsghdr *nlhdr) -{ - struct ifinfomsg *ifi; - struct rtattr *rtattr; - const char *name; - size_t remain, len; - bool set; - - ifi = (struct ifinfomsg *) NLMSG_DATA(nlhdr); - - _enter("{ix=%d}", ifi->ifi_index); - - if (ifi->ifi_index >= desc->mac_index) { - _leave(" = 0 [high]"); - return 0; - } - if (ifi->ifi_type == ARPHRD_LOOPBACK) { - _leave(" = 0 [loopback]"); - return 0; - } - - rtattr = NLMSG_DATA(nlhdr) + NLMSG_ALIGN(sizeof(struct ifinfomsg)); - remain = NLMSG_PAYLOAD(nlhdr, sizeof(struct ifinfomsg)); - - name = "unknown"; - set = false; - for (; RTA_OK(rtattr, remain); rtattr = RTA_NEXT(rtattr, remain)) { - switch (rtattr->rta_type) { - case IFLA_ADDRESS: - len = RTA_PAYLOAD(rtattr); - memcpy(desc->mac, RTA_DATA(rtattr), - min_t(size_t, len, 6)); - desc->mac_index = ifi->ifi_index; - set = true; - break; - case IFLA_IFNAME: - name = RTA_DATA(rtattr); - break; - } - } - - if (set) - _debug("%s: %02x:%02x:%02x:%02x:%02x:%02x", - name, - desc->mac[0], desc->mac[1], desc->mac[2], - desc->mac[3], desc->mac[4], desc->mac[5]); - - _leave(" = 0"); - return 0; -} - -/* - * read the rtnetlink response and pass to parsing routine - */ -static int afs_read_rtm(struct afs_rtm_desc *desc) -{ - struct nlmsghdr *nlhdr, tmphdr; - struct msghdr msg; - struct kvec iov[1]; - void *data; - bool last = false; - int len, ret, remain; - - _enter(""); - - do { - /* first of all peek to see how big the packet is */ - memset(&msg, 0, sizeof(msg)); - iov[0].iov_base = &tmphdr; - iov[0].iov_len = sizeof(tmphdr); - len = kernel_recvmsg(desc->nlsock, &msg, iov, 1, - sizeof(tmphdr), MSG_PEEK | MSG_TRUNC); - if (len < 0) { - _leave(" = %d [peek]", len); - return len; - } - if (len == 0) - continue; - if (len < sizeof(tmphdr) || len < NLMSG_PAYLOAD(&tmphdr, 0)) { - _leave(" = -EMSGSIZE"); - return -EMSGSIZE; - } - - if (desc->datamax < len) { - kfree(desc->data); - desc->data = NULL; - data = kmalloc(len, GFP_KERNEL); - if (!data) - return -ENOMEM; - desc->data = data; - } - desc->datamax = len; - - /* read all the data from this packet */ - iov[0].iov_base = desc->data; - iov[0].iov_len = desc->datamax; - desc->datalen = kernel_recvmsg(desc->nlsock, &msg, iov, 1, - desc->datamax, 0); - if (desc->datalen < 0) { - _leave(" = %zd [recv]", desc->datalen); - return desc->datalen; - } - - nlhdr = desc->data; - - /* check if the header is valid */ - if (!NLMSG_OK(nlhdr, desc->datalen) || - nlhdr->nlmsg_type == NLMSG_ERROR) { - _leave(" = -EIO"); - return -EIO; - } - - /* see if this is the last message */ - if (nlhdr->nlmsg_type == NLMSG_DONE || - !(nlhdr->nlmsg_flags & NLM_F_MULTI)) - last = true; - - /* parse the bits we got this time */ - nlmsg_for_each_msg(nlhdr, desc->data, desc->datalen, remain) { - ret = desc->parse(desc, nlhdr); - if (ret < 0) { - _leave(" = %d [parse]", ret); - return ret; - } - } - - } while (!last); - - _leave(" = 0"); - return 0; -} - -/* - * list the interface bound addresses to get the address and netmask - */ -static int afs_rtm_getaddr(struct afs_rtm_desc *desc) -{ - struct msghdr msg; - struct kvec iov[1]; - int ret; - - struct { - struct nlmsghdr nl_msg __attribute__((aligned(NLMSG_ALIGNTO))); - struct ifaddrmsg addr_msg __attribute__((aligned(NLMSG_ALIGNTO))); - } request; - - _enter(""); - - memset(&request, 0, sizeof(request)); - - request.nl_msg.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifaddrmsg)); - request.nl_msg.nlmsg_type = RTM_GETADDR; - request.nl_msg.nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP; - request.nl_msg.nlmsg_seq = desc->msg_seq++; - request.nl_msg.nlmsg_pid = 0; - - memset(&msg, 0, sizeof(msg)); - iov[0].iov_base = &request; - iov[0].iov_len = sizeof(request); - - ret = kernel_sendmsg(desc->nlsock, &msg, iov, 1, iov[0].iov_len); - _leave(" = %d", ret); - return ret; -} - -/* - * list the interface link statuses to get the MTUs - */ -static int afs_rtm_getlink(struct afs_rtm_desc *desc) -{ - struct msghdr msg; - struct kvec iov[1]; - int ret; - - struct { - struct nlmsghdr nl_msg __attribute__((aligned(NLMSG_ALIGNTO))); - struct ifinfomsg link_msg __attribute__((aligned(NLMSG_ALIGNTO))); - } request; - - _enter(""); - - memset(&request, 0, sizeof(request)); - - request.nl_msg.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); - request.nl_msg.nlmsg_type = RTM_GETLINK; - request.nl_msg.nlmsg_flags = NLM_F_REQUEST | NLM_F_ROOT; - request.nl_msg.nlmsg_seq = desc->msg_seq++; - request.nl_msg.nlmsg_pid = 0; - - memset(&msg, 0, sizeof(msg)); - iov[0].iov_base = &request; - iov[0].iov_len = sizeof(request); - - ret = kernel_sendmsg(desc->nlsock, &msg, iov, 1, iov[0].iov_len); - _leave(" = %d", ret); - return ret; -} - -/* - * cull any interface records for which there isn't an MTU value - */ -static void afs_cull_interfaces(struct afs_rtm_desc *desc) -{ - struct afs_interface *bufs = desc->bufs; - size_t nbufs = desc->nbufs; - int loop, point = 0; - - _enter("{%zu}", nbufs); - - for (loop = 0; loop < nbufs; loop++) { - if (desc->bufs[loop].mtu != 0) { - if (loop != point) { - ASSERTCMP(loop, >, point); - bufs[point] = bufs[loop]; - } - point++; - } - } - - desc->nbufs = point; - _leave(" [%zu/%zu]", desc->nbufs, nbufs); -} - -/* - * get a list of this system's interface IPv4 addresses, netmasks and MTUs - * - returns the number of interface records in the buffer - */ -int afs_get_ipv4_interfaces(struct afs_interface *bufs, size_t maxbufs, - bool wantloopback) -{ - struct afs_rtm_desc desc; - int ret, loop; - - _enter(""); - - memset(&desc, 0, sizeof(desc)); - desc.bufs = bufs; - desc.maxbufs = maxbufs; - desc.wantloopback = wantloopback; - - ret = sock_create_kern(AF_NETLINK, SOCK_DGRAM, NETLINK_ROUTE, - &desc.nlsock); - if (ret < 0) { - _leave(" = %d [sock]", ret); - return ret; - } - - /* issue RTM_GETADDR */ - desc.parse = afs_rtm_getaddr_parse; - ret = afs_rtm_getaddr(&desc); - if (ret < 0) - goto error; - ret = afs_read_rtm(&desc); - if (ret < 0) - goto error; - - /* issue RTM_GETLINK */ - desc.parse = afs_rtm_getlink_if_parse; - ret = afs_rtm_getlink(&desc); - if (ret < 0) - goto error; - ret = afs_read_rtm(&desc); - if (ret < 0) - goto error; - - afs_cull_interfaces(&desc); - ret = desc.nbufs; - - for (loop = 0; loop < ret; loop++) - _debug("[%d] "NIPQUAD_FMT"/"NIPQUAD_FMT" mtu %u", - bufs[loop].index, - NIPQUAD(bufs[loop].address), - NIPQUAD(bufs[loop].netmask), - bufs[loop].mtu); - -error: - kfree(desc.data); - sock_release(desc.nlsock); - _leave(" = %d", ret); - return ret; -} - -/* - * get a MAC address from a random ethernet interface that has a real one - * - the buffer should be 6 bytes in size - */ -int afs_get_MAC_address(u8 mac[6]) -{ - struct afs_rtm_desc desc; - int ret; - - _enter(""); - - memset(&desc, 0, sizeof(desc)); - desc.mac = mac; - desc.mac_index = UINT_MAX; - - ret = sock_create_kern(AF_NETLINK, SOCK_DGRAM, NETLINK_ROUTE, - &desc.nlsock); - if (ret < 0) { - _leave(" = %d [sock]", ret); - return ret; - } - - /* issue RTM_GETLINK */ - desc.parse = afs_rtm_getlink_mac_parse; - ret = afs_rtm_getlink(&desc); - if (ret < 0) - goto error; - ret = afs_read_rtm(&desc); - if (ret < 0) - goto error; - - if (desc.mac_index < UINT_MAX) { - /* got a MAC address */ - _debug("[%d] %02x:%02x:%02x:%02x:%02x:%02x", - desc.mac_index, - mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]); - } else { - ret = -ENONET; - } - -error: - sock_release(desc.nlsock); - _leave(" = %d", ret); - return ret; -} diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c index 6c8e95a..3370cdb 100644 --- a/fs/afs/vlocation.c +++ b/fs/afs/vlocation.c @@ -602,7 +602,7 @@ int __init afs_vlocation_update_init(void) /* * discard all the volume location records for rmmod */ -void __exit afs_vlocation_purge(void) +void afs_vlocation_purge(void) { afs_vlocation_timeout = 0; diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index 6f57300..b00d962 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -140,7 +140,7 @@ static int __init configfs_init(void) if (!configfs_dir_cachep) goto out; - kset_set_kset_s(&config_subsys, kernel_subsys); + kobj_set_kset_s(&config_subsys, kernel_subsys); err = subsystem_register(&config_subsys); if (err) { kmem_cache_destroy(configfs_dir_cachep); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 7b324cf..ec8896b 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -374,7 +374,7 @@ static int __init debugfs_init(void) { int retval; - kset_set_kset_s(&debug_subsys, kernel_subsys); + kobj_set_kset_s(&debug_subsys, kernel_subsys); retval = subsystem_register(&debug_subsys); if (retval) return retval; diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index f40817b..8e6ad76 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -167,7 +167,6 @@ static struct kobj_type dlm_ktype = { }; static struct kset dlm_kset = { - .subsys = &kernel_subsys, .kobj = {.name = "dlm",}, .ktype = &dlm_ktype, }; @@ -218,6 +217,7 @@ int dlm_lockspace_init(void) INIT_LIST_HEAD(&lslist); spin_lock_init(&lslist_lock); + kobj_set_kset_s(&dlm_kset, kernel_subsys); error = kset_register(&dlm_kset); if (error) printk("dlm_lockspace_init: cannot register kset %d\n", error); diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index fc4a3a2..6acc8f4 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -793,7 +793,7 @@ static int do_sysfs_registration(void) "Unable to register ecryptfs sysfs subsystem\n"); goto out; } - rc = sysfs_create_file(&ecryptfs_subsys.kset.kobj, + rc = sysfs_create_file(&ecryptfs_subsys.kobj, &sysfs_attr_version.attr); if (rc) { printk(KERN_ERR @@ -801,12 +801,12 @@ static int do_sysfs_registration(void) subsystem_unregister(&ecryptfs_subsys); goto out; } - rc = sysfs_create_file(&ecryptfs_subsys.kset.kobj, + rc = sysfs_create_file(&ecryptfs_subsys.kobj, &sysfs_attr_version_str.attr); if (rc) { printk(KERN_ERR "Unable to create ecryptfs version_str attribute\n"); - sysfs_remove_file(&ecryptfs_subsys.kset.kobj, + sysfs_remove_file(&ecryptfs_subsys.kobj, &sysfs_attr_version.attr); subsystem_unregister(&ecryptfs_subsys); goto out; @@ -841,7 +841,7 @@ static int __init ecryptfs_init(void) ecryptfs_free_kmem_caches(); goto out; } - kset_set_kset_s(&ecryptfs_subsys, fs_subsys); + kobj_set_kset_s(&ecryptfs_subsys, fs_subsys); sysfs_attr_version.attr.owner = THIS_MODULE; sysfs_attr_version_str.attr.owner = THIS_MODULE; rc = do_sysfs_registration(); @@ -862,9 +862,9 @@ out: static void __exit ecryptfs_exit(void) { - sysfs_remove_file(&ecryptfs_subsys.kset.kobj, + sysfs_remove_file(&ecryptfs_subsys.kobj, &sysfs_attr_version.attr); - sysfs_remove_file(&ecryptfs_subsys.kset.kobj, + sysfs_remove_file(&ecryptfs_subsys.kobj, &sysfs_attr_version_str.attr); subsystem_unregister(&ecryptfs_subsys); ecryptfs_release_messaging(ecryptfs_transport); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 608db81..bdffe0c 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -731,12 +731,12 @@ static int fuse_sysfs_init(void) { int err; - kset_set_kset_s(&fuse_subsys, fs_subsys); + kobj_set_kset_s(&fuse_subsys, fs_subsys); err = subsystem_register(&fuse_subsys); if (err) goto out_err; - kset_set_kset_s(&connections_subsys, fuse_subsys); + kobj_set_kset_s(&connections_subsys, fuse_subsys); err = subsystem_register(&connections_subsys); if (err) goto out_fuse_unregister; diff --git a/fs/gfs2/locking/dlm/sysfs.c b/fs/gfs2/locking/dlm/sysfs.c index 4746b88..d9fe3ca 100644 --- a/fs/gfs2/locking/dlm/sysfs.c +++ b/fs/gfs2/locking/dlm/sysfs.c @@ -190,7 +190,6 @@ static struct kobj_type gdlm_ktype = { }; static struct kset gdlm_kset = { - .subsys = &kernel_subsys, .kobj = {.name = "lock_dlm",}, .ktype = &gdlm_ktype, }; @@ -225,6 +224,7 @@ int gdlm_sysfs_init(void) { int error; + kobj_set_kset_s(&gdlm_kset, kernel_subsys); error = kset_register(&gdlm_kset); if (error) printk("lock_dlm: cannot register kset %d\n", error); diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index d01f9f0..c26c21b 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -222,7 +222,6 @@ static struct kobj_type gfs2_ktype = { }; static struct kset gfs2_kset = { - .subsys = &fs_subsys, .kobj = {.name = "gfs2"}, .ktype = &gfs2_ktype, }; @@ -554,6 +553,7 @@ int gfs2_sys_init(void) { gfs2_sys_margs = NULL; spin_lock_init(&gfs2_sys_margs_lock); + kobj_set_kset_s(&gfs2_kset, fs_subsys); return kset_register(&gfs2_kset); } diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index eb243ed..2102e2d 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -225,16 +225,13 @@ xdr_decode_stat(struct rpc_rqst *rqstp, __be32 *p, struct nsm_res *resp) #define SM_monres_sz 2 #define SM_unmonres_sz 1 -#ifndef MAX -# define MAX(a, b) (((a) > (b))? (a) : (b)) -#endif - static struct rpc_procinfo nsm_procedures[] = { [SM_MON] = { .p_proc = SM_MON, .p_encode = (kxdrproc_t) xdr_encode_mon, .p_decode = (kxdrproc_t) xdr_decode_stat_res, - .p_bufsiz = MAX(SM_mon_sz, SM_monres_sz) << 2, + .p_arglen = SM_mon_sz, + .p_replen = SM_monres_sz, .p_statidx = SM_MON, .p_name = "MONITOR", }, @@ -242,7 +239,8 @@ static struct rpc_procinfo nsm_procedures[] = { .p_proc = SM_UNMON, .p_encode = (kxdrproc_t) xdr_encode_unmon, .p_decode = (kxdrproc_t) xdr_decode_stat, - .p_bufsiz = MAX(SM_mon_id_sz, SM_unmonres_sz) << 2, + .p_arglen = SM_mon_id_sz, + .p_replen = SM_unmonres_sz, .p_statidx = SM_UNMON, .p_name = "UNMONITOR", }, diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 34dae5d..9702956 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -510,17 +510,20 @@ nlmclt_decode_res(struct rpc_rqst *req, __be32 *p, struct nlm_res *resp) return 0; } +#if (NLMCLNT_OHSIZE > XDR_MAX_NETOBJ) +# error "NLM host name cannot be larger than XDR_MAX_NETOBJ!" +#endif + /* * Buffer requirements for NLM */ #define NLM_void_sz 0 #define NLM_cookie_sz 1+XDR_QUADLEN(NLM_MAXCOOKIELEN) -#define NLM_caller_sz 1+XDR_QUADLEN(sizeof(utsname()->nodename)) -#define NLM_netobj_sz 1+XDR_QUADLEN(XDR_MAX_NETOBJ) -/* #define NLM_owner_sz 1+XDR_QUADLEN(NLM_MAXOWNER) */ +#define NLM_caller_sz 1+XDR_QUADLEN(NLMCLNT_OHSIZE) +#define NLM_owner_sz 1+XDR_QUADLEN(NLMCLNT_OHSIZE) #define NLM_fhandle_sz 1+XDR_QUADLEN(NFS2_FHSIZE) -#define NLM_lock_sz 3+NLM_caller_sz+NLM_netobj_sz+NLM_fhandle_sz -#define NLM_holder_sz 4+NLM_netobj_sz +#define NLM_lock_sz 3+NLM_caller_sz+NLM_owner_sz+NLM_fhandle_sz +#define NLM_holder_sz 4+NLM_owner_sz #define NLM_testargs_sz NLM_cookie_sz+1+NLM_lock_sz #define NLM_lockargs_sz NLM_cookie_sz+4+NLM_lock_sz @@ -531,10 +534,6 @@ nlmclt_decode_res(struct rpc_rqst *req, __be32 *p, struct nlm_res *resp) #define NLM_res_sz NLM_cookie_sz+1 #define NLM_norep_sz 0 -#ifndef MAX -# define MAX(a, b) (((a) > (b))? (a) : (b)) -#endif - /* * For NLM, a void procedure really returns nothing */ @@ -545,7 +544,8 @@ nlmclt_decode_res(struct rpc_rqst *req, __be32 *p, struct nlm_res *resp) .p_proc = NLMPROC_##proc, \ .p_encode = (kxdrproc_t) nlmclt_encode_##argtype, \ .p_decode = (kxdrproc_t) nlmclt_decode_##restype, \ - .p_bufsiz = MAX(NLM_##argtype##_sz, NLM_##restype##_sz) << 2, \ + .p_arglen = NLM_##argtype##_sz, \ + .p_replen = NLM_##restype##_sz, \ .p_statidx = NLMPROC_##proc, \ .p_name = #proc, \ } diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index a782405..ce1efdb 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -516,17 +516,24 @@ nlm4clt_decode_res(struct rpc_rqst *req, __be32 *p, struct nlm_res *resp) return 0; } +#if (NLMCLNT_OHSIZE > XDR_MAX_NETOBJ) +# error "NLM host name cannot be larger than XDR_MAX_NETOBJ!" +#endif + +#if (NLMCLNT_OHSIZE > NLM_MAXSTRLEN) +# error "NLM host name cannot be larger than NLM's maximum string length!" +#endif + /* * Buffer requirements for NLM */ #define NLM4_void_sz 0 #define NLM4_cookie_sz 1+XDR_QUADLEN(NLM_MAXCOOKIELEN) -#define NLM4_caller_sz 1+XDR_QUADLEN(NLM_MAXSTRLEN) -#define NLM4_netobj_sz 1+XDR_QUADLEN(XDR_MAX_NETOBJ) -/* #define NLM4_owner_sz 1+XDR_QUADLEN(NLM4_MAXOWNER) */ +#define NLM4_caller_sz 1+XDR_QUADLEN(NLMCLNT_OHSIZE) +#define NLM4_owner_sz 1+XDR_QUADLEN(NLMCLNT_OHSIZE) #define NLM4_fhandle_sz 1+XDR_QUADLEN(NFS3_FHSIZE) -#define NLM4_lock_sz 5+NLM4_caller_sz+NLM4_netobj_sz+NLM4_fhandle_sz -#define NLM4_holder_sz 6+NLM4_netobj_sz +#define NLM4_lock_sz 5+NLM4_caller_sz+NLM4_owner_sz+NLM4_fhandle_sz +#define NLM4_holder_sz 6+NLM4_owner_sz #define NLM4_testargs_sz NLM4_cookie_sz+1+NLM4_lock_sz #define NLM4_lockargs_sz NLM4_cookie_sz+4+NLM4_lock_sz @@ -537,10 +544,6 @@ nlm4clt_decode_res(struct rpc_rqst *req, __be32 *p, struct nlm_res *resp) #define NLM4_res_sz NLM4_cookie_sz+1 #define NLM4_norep_sz 0 -#ifndef MAX -# define MAX(a,b) (((a) > (b))? (a) : (b)) -#endif - /* * For NLM, a void procedure really returns nothing */ @@ -551,7 +554,8 @@ nlm4clt_decode_res(struct rpc_rqst *req, __be32 *p, struct nlm_res *resp) .p_proc = NLMPROC_##proc, \ .p_encode = (kxdrproc_t) nlm4clt_encode_##argtype, \ .p_decode = (kxdrproc_t) nlm4clt_decode_##restype, \ - .p_bufsiz = MAX(NLM4_##argtype##_sz, NLM4_##restype##_sz) << 2, \ + .p_arglen = NLM4_##argtype##_sz, \ + .p_replen = NLM4_##restype##_sz, \ .p_statidx = NLMPROC_##proc, \ .p_name = #proc, \ } diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 2190e6c..5bd03b9 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -618,7 +618,8 @@ static int nfs_init_server(struct nfs_server *server, const struct nfs_mount_dat if (clp->cl_nfsversion == 3) { if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN) server->namelen = NFS3_MAXNAMLEN; - server->caps |= NFS_CAP_READDIRPLUS; + if (!(data->flags & NFS_MOUNT_NORDIRPLUS)) + server->caps |= NFS_CAP_READDIRPLUS; } else { if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN) server->namelen = NFS2_MAXNAMLEN; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index cd34697..e59fd31 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -154,6 +154,8 @@ typedef struct { decode_dirent_t decode; int plus; int error; + unsigned long timestamp; + int timestamp_valid; } nfs_readdir_descriptor_t; /* Now we cache directories properly, by stuffing the dirent @@ -195,6 +197,8 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page *page) } goto error; } + desc->timestamp = timestamp; + desc->timestamp_valid = 1; SetPageUptodate(page); spin_lock(&inode->i_lock); NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATIME; @@ -225,6 +229,10 @@ int dir_decode(nfs_readdir_descriptor_t *desc) if (IS_ERR(p)) return PTR_ERR(p); desc->ptr = p; + if (desc->timestamp_valid) + desc->entry->fattr->time_start = desc->timestamp; + else + desc->entry->fattr->valid &= ~NFS_ATTR_FATTR; return 0; } @@ -316,6 +324,10 @@ int find_dirent_page(nfs_readdir_descriptor_t *desc) __FUNCTION__, desc->page_index, (long long) *desc->dir_cookie); + /* If we find the page in the page_cache, we cannot be sure + * how fresh the data is, so we will ignore readdir_plus attributes. + */ + desc->timestamp_valid = 0; page = read_cache_page(inode->i_mapping, desc->page_index, (filler_t *)nfs_readdir_filler, desc); if (IS_ERR(page)) { @@ -468,6 +480,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent, struct rpc_cred *cred = nfs_file_cred(file); struct page *page = NULL; int status; + unsigned long timestamp; dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %Lu\n", (unsigned long long)*desc->dir_cookie); @@ -477,6 +490,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent, status = -ENOMEM; goto out; } + timestamp = jiffies; desc->error = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred, *desc->dir_cookie, page, NFS_SERVER(inode)->dtsize, @@ -487,6 +501,8 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent, desc->page = page; desc->ptr = kmap(page); /* matching kunmap in nfs_do_filldir */ if (desc->error >= 0) { + desc->timestamp = timestamp; + desc->timestamp_valid = 1; if ((status = dir_decode(desc)) == 0) desc->entry->prev_cookie = *desc->dir_cookie; } else @@ -849,6 +865,10 @@ static int nfs_dentry_delete(struct dentry *dentry) static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode) { nfs_inode_return_delegation(inode); + if (S_ISDIR(inode->i_mode)) + /* drop any readdir cache as it could easily be old */ + NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA; + if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { lock_kernel(); drop_nlink(inode); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 2877744c..889de60 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -54,6 +54,7 @@ #include <asm/uaccess.h> #include <asm/atomic.h> +#include "internal.h" #include "iostat.h" #define NFSDBG_FACILITY NFSDBG_VFS @@ -271,7 +272,7 @@ static ssize_t nfs_direct_read_schedule(struct nfs_direct_req *dreq, unsigned lo bytes = min(rsize,count); result = -ENOMEM; - data = nfs_readdata_alloc(pgbase + bytes); + data = nfs_readdata_alloc(nfs_page_array_len(pgbase, bytes)); if (unlikely(!data)) break; @@ -602,7 +603,7 @@ static ssize_t nfs_direct_write_schedule(struct nfs_direct_req *dreq, unsigned l bytes = min(wsize,count); result = -ENOMEM; - data = nfs_writedata_alloc(pgbase + bytes); + data = nfs_writedata_alloc(nfs_page_array_len(pgbase, bytes)); if (unlikely(!data)) break; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 6610f2b..ad2b40d 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -231,3 +231,15 @@ unsigned int nfs_page_length(struct page *page) } return 0; } + +/* + * Determine the number of pages in an array of length 'len' and + * with a base offset of 'base' + */ +static inline +unsigned int nfs_page_array_len(unsigned int base, size_t len) +{ + return ((unsigned long)len + (unsigned long)base + + PAGE_SIZE - 1) >> PAGE_SHIFT; +} + diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index f75fe72..ca5a266 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -133,13 +133,15 @@ xdr_decode_fhstatus3(struct rpc_rqst *req, __be32 *p, struct mnt_fhstatus *res) #define MNT_dirpath_sz (1 + 256) #define MNT_fhstatus_sz (1 + 8) +#define MNT_fhstatus3_sz (1 + 16) static struct rpc_procinfo mnt_procedures[] = { [MNTPROC_MNT] = { .p_proc = MNTPROC_MNT, .p_encode = (kxdrproc_t) xdr_encode_dirpath, .p_decode = (kxdrproc_t) xdr_decode_fhstatus, - .p_bufsiz = MNT_dirpath_sz << 2, + .p_arglen = MNT_dirpath_sz, + .p_replen = MNT_fhstatus_sz, .p_statidx = MNTPROC_MNT, .p_name = "MOUNT", }, @@ -150,7 +152,8 @@ static struct rpc_procinfo mnt3_procedures[] = { .p_proc = MOUNTPROC3_MNT, .p_encode = (kxdrproc_t) xdr_encode_dirpath, .p_decode = (kxdrproc_t) xdr_decode_fhstatus3, - .p_bufsiz = MNT_dirpath_sz << 2, + .p_arglen = MNT_dirpath_sz, + .p_replen = MNT_fhstatus3_sz, .p_statidx = MOUNTPROC3_MNT, .p_name = "MOUNT", }, diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 3be4e72..abd9f8b 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -687,16 +687,13 @@ nfs_stat_to_errno(int stat) return nfs_errtbl[i].errno; } -#ifndef MAX -# define MAX(a, b) (((a) > (b))? (a) : (b)) -#endif - #define PROC(proc, argtype, restype, timer) \ [NFSPROC_##proc] = { \ .p_proc = NFSPROC_##proc, \ .p_encode = (kxdrproc_t) nfs_xdr_##argtype, \ .p_decode = (kxdrproc_t) nfs_xdr_##restype, \ - .p_bufsiz = MAX(NFS_##argtype##_sz,NFS_##restype##_sz) << 2, \ + .p_arglen = NFS_##argtype##_sz, \ + .p_replen = NFS_##restype##_sz, \ .p_timer = timer, \ .p_statidx = NFSPROC_##proc, \ .p_name = #proc, \ diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 0ace092..b51df8e 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -1102,16 +1102,13 @@ nfs3_xdr_setaclres(struct rpc_rqst *req, __be32 *p, struct nfs_fattr *fattr) } #endif /* CONFIG_NFS_V3_ACL */ -#ifndef MAX -# define MAX(a, b) (((a) > (b))? (a) : (b)) -#endif - #define PROC(proc, argtype, restype, timer) \ [NFS3PROC_##proc] = { \ .p_proc = NFS3PROC_##proc, \ .p_encode = (kxdrproc_t) nfs3_xdr_##argtype, \ .p_decode = (kxdrproc_t) nfs3_xdr_##restype, \ - .p_bufsiz = MAX(NFS3_##argtype##_sz,NFS3_##restype##_sz) << 2, \ + .p_arglen = NFS3_##argtype##_sz, \ + .p_replen = NFS3_##restype##_sz, \ .p_timer = timer, \ .p_statidx = NFS3PROC_##proc, \ .p_name = #proc, \ @@ -1153,7 +1150,8 @@ static struct rpc_procinfo nfs3_acl_procedures[] = { .p_proc = ACLPROC3_GETACL, .p_encode = (kxdrproc_t) nfs3_xdr_getaclargs, .p_decode = (kxdrproc_t) nfs3_xdr_getaclres, - .p_bufsiz = MAX(ACL3_getaclargs_sz, ACL3_getaclres_sz) << 2, + .p_arglen = ACL3_getaclargs_sz, + .p_replen = ACL3_getaclres_sz, .p_timer = 1, .p_name = "GETACL", }, @@ -1161,7 +1159,8 @@ static struct rpc_procinfo nfs3_acl_procedures[] = { .p_proc = ACLPROC3_SETACL, .p_encode = (kxdrproc_t) nfs3_xdr_setaclargs, .p_decode = (kxdrproc_t) nfs3_xdr_setaclres, - .p_bufsiz = MAX(ACL3_setaclargs_sz, ACL3_setaclres_sz) << 2, + .p_arglen = ACL3_setaclargs_sz, + .p_replen = ACL3_setaclres_sz, .p_timer = 0, .p_name = "SETACL", }, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f52cf5c..3b5ca1b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2647,8 +2647,7 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl nfs_inode_return_delegation(inode); buf_to_pages(buf, buflen, arg.acl_pages, &arg.acl_pgbase); ret = rpc_call_sync(NFS_CLIENT(inode), &msg, 0); - if (ret == 0) - nfs4_write_cached_acl(inode, buf, buflen); + nfs_zap_caches(inode); return ret; } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index f02d522..b8c28f2 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -4546,16 +4546,13 @@ nfs4_stat_to_errno(int stat) return stat; } -#ifndef MAX -# define MAX(a, b) (((a) > (b))? (a) : (b)) -#endif - #define PROC(proc, argtype, restype) \ [NFSPROC4_CLNT_##proc] = { \ .p_proc = NFSPROC4_COMPOUND, \ .p_encode = (kxdrproc_t) nfs4_xdr_##argtype, \ .p_decode = (kxdrproc_t) nfs4_xdr_##restype, \ - .p_bufsiz = MAX(NFS4_##argtype##_sz,NFS4_##restype##_sz) << 2, \ + .p_arglen = NFS4_##argtype##_sz, \ + .p_replen = NFS4_##restype##_sz, \ .p_statidx = NFSPROC4_CLNT_##proc, \ .p_name = #proc, \ } diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index 75f819d..49d1008 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -428,7 +428,7 @@ static int __init root_nfs_getport(int program, int version, int proto) printk(KERN_NOTICE "Looking up port of RPC %d/%d on %u.%u.%u.%u\n", program, version, NIPQUAD(servaddr)); set_sockaddr(&sin, servaddr, 0); - return rpc_getport_external(&sin, program, version, proto); + return rpcb_getport_external(&sin, program, version, proto); } diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index ca4b1d4..3889501 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -17,7 +17,8 @@ #include <linux/nfs_page.h> #include <linux/nfs_fs.h> #include <linux/nfs_mount.h> -#include <linux/writeback.h> + +#include "internal.h" #define NFS_PARANOIA 1 @@ -50,9 +51,7 @@ nfs_page_free(struct nfs_page *p) * @count: number of bytes to read/write * * The page must be locked by the caller. This makes sure we never - * create two different requests for the same page, and avoids - * a possible deadlock when we reach the hard limit on the number - * of dirty pages. + * create two different requests for the same page. * User should ensure it is safe to sleep in this function. */ struct nfs_page * @@ -63,16 +62,12 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, struct nfs_server *server = NFS_SERVER(inode); struct nfs_page *req; - /* Deal with hard limits. */ for (;;) { /* try to allocate the request struct */ req = nfs_page_alloc(); if (req != NULL) break; - /* Try to free up at least one request in order to stay - * below the hard limit - */ if (signalled() && (server->flags & NFS_MOUNT_INTR)) return ERR_PTR(-ERESTARTSYS); yield(); @@ -223,124 +218,151 @@ out: } /** - * nfs_coalesce_requests - Split coalesced requests out from a list. - * @head: source list - * @dst: destination list - * @nmax: maximum number of requests to coalesce - * - * Moves a maximum of 'nmax' elements from one list to another. - * The elements are checked to ensure that they form a contiguous set - * of pages, and that the RPC credentials are the same. + * nfs_pageio_init - initialise a page io descriptor + * @desc: pointer to descriptor + * @inode: pointer to inode + * @doio: pointer to io function + * @bsize: io block size + * @io_flags: extra parameters for the io function */ -int -nfs_coalesce_requests(struct list_head *head, struct list_head *dst, - unsigned int nmax) +void nfs_pageio_init(struct nfs_pageio_descriptor *desc, + struct inode *inode, + int (*doio)(struct inode *, struct list_head *, unsigned int, size_t, int), + size_t bsize, + int io_flags) { - struct nfs_page *req = NULL; - unsigned int npages = 0; - - while (!list_empty(head)) { - struct nfs_page *prev = req; - - req = nfs_list_entry(head->next); - if (prev) { - if (req->wb_context->cred != prev->wb_context->cred) - break; - if (req->wb_context->lockowner != prev->wb_context->lockowner) - break; - if (req->wb_context->state != prev->wb_context->state) - break; - if (req->wb_index != (prev->wb_index + 1)) - break; - - if (req->wb_pgbase != 0) - break; - } - nfs_list_remove_request(req); - nfs_list_add_request(req, dst); - npages++; - if (req->wb_pgbase + req->wb_bytes != PAGE_CACHE_SIZE) - break; - if (npages >= nmax) - break; - } - return npages; + INIT_LIST_HEAD(&desc->pg_list); + desc->pg_bytes_written = 0; + desc->pg_count = 0; + desc->pg_bsize = bsize; + desc->pg_base = 0; + desc->pg_inode = inode; + desc->pg_doio = doio; + desc->pg_ioflags = io_flags; + desc->pg_error = 0; } -#define NFS_SCAN_MAXENTRIES 16 /** - * nfs_scan_dirty - Scan the radix tree for dirty requests - * @mapping: pointer to address space - * @wbc: writeback_control structure - * @dst: Destination list + * nfs_can_coalesce_requests - test two requests for compatibility + * @prev: pointer to nfs_page + * @req: pointer to nfs_page * - * Moves elements from one of the inode request lists. - * If the number of requests is set to 0, the entire address_space - * starting at index idx_start, is scanned. - * The requests are *not* checked to ensure that they form a contiguous set. - * You must be holding the inode's req_lock when calling this function + * The nfs_page structures 'prev' and 'req' are compared to ensure that the + * page data area they describe is contiguous, and that their RPC + * credentials, NFSv4 open state, and lockowners are the same. + * + * Return 'true' if this is the case, else return 'false'. */ -long nfs_scan_dirty(struct address_space *mapping, - struct writeback_control *wbc, - struct list_head *dst) +static int nfs_can_coalesce_requests(struct nfs_page *prev, + struct nfs_page *req) { - struct nfs_inode *nfsi = NFS_I(mapping->host); - struct nfs_page *pgvec[NFS_SCAN_MAXENTRIES]; - struct nfs_page *req; - pgoff_t idx_start, idx_end; - long res = 0; - int found, i; - - if (nfsi->ndirty == 0) + if (req->wb_context->cred != prev->wb_context->cred) return 0; - if (wbc->range_cyclic) { - idx_start = 0; - idx_end = ULONG_MAX; - } else if (wbc->range_end == 0) { - idx_start = wbc->range_start >> PAGE_CACHE_SHIFT; - idx_end = ULONG_MAX; - } else { - idx_start = wbc->range_start >> PAGE_CACHE_SHIFT; - idx_end = wbc->range_end >> PAGE_CACHE_SHIFT; - } + if (req->wb_context->lockowner != prev->wb_context->lockowner) + return 0; + if (req->wb_context->state != prev->wb_context->state) + return 0; + if (req->wb_index != (prev->wb_index + 1)) + return 0; + if (req->wb_pgbase != 0) + return 0; + if (prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE) + return 0; + return 1; +} - for (;;) { - unsigned int toscan = NFS_SCAN_MAXENTRIES; +/** + * nfs_pageio_do_add_request - Attempt to coalesce a request into a page list. + * @desc: destination io descriptor + * @req: request + * + * Returns true if the request 'req' was successfully coalesced into the + * existing list of pages 'desc'. + */ +static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc, + struct nfs_page *req) +{ + size_t newlen = req->wb_bytes; - found = radix_tree_gang_lookup_tag(&nfsi->nfs_page_tree, - (void **)&pgvec[0], idx_start, toscan, - NFS_PAGE_TAG_DIRTY); + if (desc->pg_count != 0) { + struct nfs_page *prev; - /* Did we make progress? */ - if (found <= 0) - break; + /* + * FIXME: ideally we should be able to coalesce all requests + * that are not block boundary aligned, but currently this + * is problematic for the case of bsize < PAGE_CACHE_SIZE, + * since nfs_flush_multi and nfs_pagein_multi assume you + * can have only one struct nfs_page. + */ + if (desc->pg_bsize < PAGE_SIZE) + return 0; + newlen += desc->pg_count; + if (newlen > desc->pg_bsize) + return 0; + prev = nfs_list_entry(desc->pg_list.prev); + if (!nfs_can_coalesce_requests(prev, req)) + return 0; + } else + desc->pg_base = req->wb_pgbase; + nfs_list_remove_request(req); + nfs_list_add_request(req, &desc->pg_list); + desc->pg_count = newlen; + return 1; +} - for (i = 0; i < found; i++) { - req = pgvec[i]; - if (!wbc->range_cyclic && req->wb_index > idx_end) - goto out; +/* + * Helper for nfs_pageio_add_request and nfs_pageio_complete + */ +static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc) +{ + if (!list_empty(&desc->pg_list)) { + int error = desc->pg_doio(desc->pg_inode, + &desc->pg_list, + nfs_page_array_len(desc->pg_base, + desc->pg_count), + desc->pg_count, + desc->pg_ioflags); + if (error < 0) + desc->pg_error = error; + else + desc->pg_bytes_written += desc->pg_count; + } + if (list_empty(&desc->pg_list)) { + desc->pg_count = 0; + desc->pg_base = 0; + } +} - /* Try to lock request and mark it for writeback */ - if (!nfs_set_page_writeback_locked(req)) - goto next; - radix_tree_tag_clear(&nfsi->nfs_page_tree, - req->wb_index, NFS_PAGE_TAG_DIRTY); - nfsi->ndirty--; - nfs_list_remove_request(req); - nfs_list_add_request(req, dst); - res++; - if (res == LONG_MAX) - goto out; -next: - idx_start = req->wb_index + 1; - } +/** + * nfs_pageio_add_request - Attempt to coalesce a request into a page list. + * @desc: destination io descriptor + * @req: request + * + * Returns true if the request 'req' was successfully coalesced into the + * existing list of pages 'desc'. + */ +int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, + struct nfs_page *req) +{ + while (!nfs_pageio_do_add_request(desc, req)) { + nfs_pageio_doio(desc); + if (desc->pg_error < 0) + return 0; } -out: - WARN_ON ((nfsi->ndirty == 0) != list_empty(&nfsi->dirty)); - return res; + return 1; } /** + * nfs_pageio_complete - Complete I/O on an nfs_pageio_descriptor + * @desc: pointer to io descriptor + */ +void nfs_pageio_complete(struct nfs_pageio_descriptor *desc) +{ + nfs_pageio_doio(desc); +} + +#define NFS_SCAN_MAXENTRIES 16 +/** * nfs_scan_list - Scan a list for matching requests * @nfsi: NFS inode * @head: One of the NFS inode request lists @@ -355,12 +377,12 @@ out: * You must be holding the inode's req_lock when calling this function */ int nfs_scan_list(struct nfs_inode *nfsi, struct list_head *head, - struct list_head *dst, unsigned long idx_start, + struct list_head *dst, pgoff_t idx_start, unsigned int npages) { struct nfs_page *pgvec[NFS_SCAN_MAXENTRIES]; struct nfs_page *req; - unsigned long idx_end; + pgoff_t idx_end; int found, i; int res; diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 6ab4d5a..9a55807 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -27,7 +27,8 @@ #define NFSDBG_FACILITY NFSDBG_PAGECACHE -static int nfs_pagein_one(struct list_head *, struct inode *); +static int nfs_pagein_multi(struct inode *, struct list_head *, unsigned int, size_t, int); +static int nfs_pagein_one(struct inode *, struct list_head *, unsigned int, size_t, int); static const struct rpc_call_ops nfs_read_partial_ops; static const struct rpc_call_ops nfs_read_full_ops; @@ -36,9 +37,8 @@ static mempool_t *nfs_rdata_mempool; #define MIN_POOL_READ (32) -struct nfs_read_data *nfs_readdata_alloc(size_t len) +struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount) { - unsigned int pagecount = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; struct nfs_read_data *p = mempool_alloc(nfs_rdata_mempool, GFP_NOFS); if (p) { @@ -133,7 +133,10 @@ static int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, memclear_highpage_flush(page, len, PAGE_CACHE_SIZE - len); nfs_list_add_request(new, &one_request); - nfs_pagein_one(&one_request, inode); + if (NFS_SERVER(inode)->rsize < PAGE_CACHE_SIZE) + nfs_pagein_multi(inode, &one_request, 1, len, 0); + else + nfs_pagein_one(inode, &one_request, 1, len, 0); return 0; } @@ -230,7 +233,7 @@ static void nfs_execute_read(struct nfs_read_data *data) * won't see the new data until our attribute cache is updated. This is more * or less conventional NFS client behavior. */ -static int nfs_pagein_multi(struct list_head *head, struct inode *inode) +static int nfs_pagein_multi(struct inode *inode, struct list_head *head, unsigned int npages, size_t count, int flags) { struct nfs_page *req = nfs_list_entry(head->next); struct page *page = req->wb_page; @@ -242,11 +245,11 @@ static int nfs_pagein_multi(struct list_head *head, struct inode *inode) nfs_list_remove_request(req); - nbytes = req->wb_bytes; + nbytes = count; do { size_t len = min(nbytes,rsize); - data = nfs_readdata_alloc(len); + data = nfs_readdata_alloc(1); if (!data) goto out_bad; INIT_LIST_HEAD(&data->pages); @@ -258,23 +261,19 @@ static int nfs_pagein_multi(struct list_head *head, struct inode *inode) ClearPageError(page); offset = 0; - nbytes = req->wb_bytes; + nbytes = count; do { data = list_entry(list.next, struct nfs_read_data, pages); list_del_init(&data->pages); data->pagevec[0] = page; - if (nbytes > rsize) { - nfs_read_rpcsetup(req, data, &nfs_read_partial_ops, - rsize, offset); - offset += rsize; - nbytes -= rsize; - } else { - nfs_read_rpcsetup(req, data, &nfs_read_partial_ops, - nbytes, offset); - nbytes = 0; - } + if (nbytes < rsize) + rsize = nbytes; + nfs_read_rpcsetup(req, data, &nfs_read_partial_ops, + rsize, offset); + offset += rsize; + nbytes -= rsize; nfs_execute_read(data); } while (nbytes != 0); @@ -291,30 +290,24 @@ out_bad: return -ENOMEM; } -static int nfs_pagein_one(struct list_head *head, struct inode *inode) +static int nfs_pagein_one(struct inode *inode, struct list_head *head, unsigned int npages, size_t count, int flags) { struct nfs_page *req; struct page **pages; struct nfs_read_data *data; - unsigned int count; - if (NFS_SERVER(inode)->rsize < PAGE_CACHE_SIZE) - return nfs_pagein_multi(head, inode); - - data = nfs_readdata_alloc(NFS_SERVER(inode)->rsize); + data = nfs_readdata_alloc(npages); if (!data) goto out_bad; INIT_LIST_HEAD(&data->pages); pages = data->pagevec; - count = 0; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); nfs_list_add_request(req, &data->pages); ClearPageError(req->wb_page); *pages++ = req->wb_page; - count += req->wb_bytes; } req = nfs_list_entry(data->pages.next); @@ -327,28 +320,6 @@ out_bad: return -ENOMEM; } -static int -nfs_pagein_list(struct list_head *head, int rpages) -{ - LIST_HEAD(one_request); - struct nfs_page *req; - int error = 0; - unsigned int pages = 0; - - while (!list_empty(head)) { - pages += nfs_coalesce_requests(head, &one_request, rpages); - req = nfs_list_entry(one_request.next); - error = nfs_pagein_one(&one_request, req->wb_context->dentry->d_inode); - if (error < 0) - break; - } - if (error >= 0) - return pages; - - nfs_async_read_error(head); - return error; -} - /* * This is the callback from RPC telling us whether a reply was * received or some error occurred (timeout or socket shutdown). @@ -538,7 +509,7 @@ out_error: } struct nfs_readdesc { - struct list_head *head; + struct nfs_pageio_descriptor *pgio; struct nfs_open_context *ctx; }; @@ -562,19 +533,21 @@ readpage_async_filler(void *data, struct page *page) } if (len < PAGE_CACHE_SIZE) memclear_highpage_flush(page, len, PAGE_CACHE_SIZE - len); - nfs_list_add_request(new, desc->head); + nfs_pageio_add_request(desc->pgio, new); return 0; } int nfs_readpages(struct file *filp, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { - LIST_HEAD(head); + struct nfs_pageio_descriptor pgio; struct nfs_readdesc desc = { - .head = &head, + .pgio = &pgio, }; struct inode *inode = mapping->host; struct nfs_server *server = NFS_SERVER(inode); + size_t rsize = server->rsize; + unsigned long npages; int ret = -ESTALE; dprintk("NFS: nfs_readpages (%s/%Ld %d)\n", @@ -593,13 +566,16 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, } else desc.ctx = get_nfs_open_context((struct nfs_open_context *) filp->private_data); + if (rsize < PAGE_CACHE_SIZE) + nfs_pageio_init(&pgio, inode, nfs_pagein_multi, rsize, 0); + else + nfs_pageio_init(&pgio, inode, nfs_pagein_one, rsize, 0); + ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); - if (!list_empty(&head)) { - int err = nfs_pagein_list(&head, server->rpages); - if (!ret) - nfs_add_stats(inode, NFSIOS_READPAGES, err); - ret = err; - } + + nfs_pageio_complete(&pgio); + npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + nfs_add_stats(inode, NFSIOS_READPAGES, npages); put_nfs_open_context(desc.ctx); out: return ret; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index f1eae44..ca20d3c 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -204,9 +204,9 @@ static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf) lock_kernel(); error = server->nfs_client->rpc_ops->statfs(server, fh, &res); - buf->f_type = NFS_SUPER_MAGIC; if (error < 0) goto out_err; + buf->f_type = NFS_SUPER_MAGIC; /* * Current versions of glibc do not correctly handle the @@ -233,15 +233,14 @@ static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_ffree = res.afiles; buf->f_namelen = server->namelen; - out: + unlock_kernel(); return 0; out_err: dprintk("%s: statfs error = %d\n", __FUNCTION__, -error); - buf->f_bsize = buf->f_blocks = buf->f_bfree = buf->f_bavail = -1; - goto out; - + unlock_kernel(); + return error; } /* @@ -291,6 +290,7 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, { NFS_MOUNT_NOAC, ",noac", "" }, { NFS_MOUNT_NONLM, ",nolock", "" }, { NFS_MOUNT_NOACL, ",noacl", "" }, + { NFS_MOUNT_NORDIRPLUS, ",nordirplus", "" }, { 0, NULL, NULL } }; const struct proc_nfs_info *nfs_infop; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 7975589..5d44b8b 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -38,7 +38,8 @@ static struct nfs_page * nfs_update_request(struct nfs_open_context*, struct page *, unsigned int, unsigned int); -static long nfs_flush_mapping(struct address_space *mapping, struct writeback_control *wbc, int how); +static void nfs_pageio_init_write(struct nfs_pageio_descriptor *desc, + struct inode *inode, int ioflags); static const struct rpc_call_ops nfs_write_partial_ops; static const struct rpc_call_ops nfs_write_full_ops; static const struct rpc_call_ops nfs_commit_ops; @@ -71,9 +72,8 @@ void nfs_commit_free(struct nfs_write_data *wdata) call_rcu_bh(&wdata->task.u.tk_rcu, nfs_commit_rcu_free); } -struct nfs_write_data *nfs_writedata_alloc(size_t len) +struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount) { - unsigned int pagecount = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; struct nfs_write_data *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS); if (p) { @@ -139,7 +139,7 @@ static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int c { struct inode *inode = page->mapping->host; loff_t end, i_size = i_size_read(inode); - unsigned long end_index = (i_size - 1) >> PAGE_CACHE_SHIFT; + pgoff_t end_index = (i_size - 1) >> PAGE_CACHE_SHIFT; if (i_size > 0 && page->index < end_index) return; @@ -201,7 +201,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page, static int wb_priority(struct writeback_control *wbc) { if (wbc->for_reclaim) - return FLUSH_HIGHPRI; + return FLUSH_HIGHPRI | FLUSH_STABLE; if (wbc->for_kupdate) return FLUSH_LOWPRI; return 0; @@ -251,7 +251,8 @@ static void nfs_end_page_writeback(struct page *page) * was not tagged. * May also return an error if the user signalled nfs_wait_on_request(). */ -static int nfs_page_mark_flush(struct page *page) +static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, + struct page *page) { struct nfs_page *req; struct nfs_inode *nfsi = NFS_I(page->mapping->host); @@ -273,6 +274,8 @@ static int nfs_page_mark_flush(struct page *page) * request as dirty (in which case we don't care). */ spin_unlock(req_lock); + /* Prevent deadlock! */ + nfs_pageio_complete(pgio); ret = nfs_wait_on_request(req); nfs_release_request(req); if (ret != 0) @@ -283,21 +286,18 @@ static int nfs_page_mark_flush(struct page *page) /* This request is marked for commit */ spin_unlock(req_lock); nfs_unlock_request(req); + nfs_pageio_complete(pgio); return 1; } - if (nfs_set_page_writeback(page) == 0) { - nfs_list_remove_request(req); - /* add the request to the inode's dirty list. */ - radix_tree_tag_set(&nfsi->nfs_page_tree, - req->wb_index, NFS_PAGE_TAG_DIRTY); - nfs_list_add_request(req, &nfsi->dirty); - nfsi->ndirty++; - spin_unlock(req_lock); - __mark_inode_dirty(page->mapping->host, I_DIRTY_PAGES); - } else + if (nfs_set_page_writeback(page) != 0) { spin_unlock(req_lock); + BUG(); + } + radix_tree_tag_set(&nfsi->nfs_page_tree, req->wb_index, + NFS_PAGE_TAG_WRITEBACK); ret = test_bit(PG_NEED_FLUSH, &req->wb_flags); - nfs_unlock_request(req); + spin_unlock(req_lock); + nfs_pageio_add_request(pgio, req); return ret; } @@ -306,6 +306,7 @@ static int nfs_page_mark_flush(struct page *page) */ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc) { + struct nfs_pageio_descriptor mypgio, *pgio; struct nfs_open_context *ctx; struct inode *inode = page->mapping->host; unsigned offset; @@ -314,7 +315,14 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1); - err = nfs_page_mark_flush(page); + if (wbc->for_writepages) + pgio = wbc->fs_private; + else { + nfs_pageio_init_write(&mypgio, inode, wb_priority(wbc)); + pgio = &mypgio; + } + + err = nfs_page_async_flush(pgio, page); if (err <= 0) goto out; err = 0; @@ -331,12 +339,12 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc put_nfs_open_context(ctx); if (err != 0) goto out; - err = nfs_page_mark_flush(page); + err = nfs_page_async_flush(pgio, page); if (err > 0) err = 0; out: if (!wbc->for_writepages) - nfs_flush_mapping(page->mapping, wbc, FLUSH_STABLE|wb_priority(wbc)); + nfs_pageio_complete(pgio); return err; } @@ -352,20 +360,20 @@ int nfs_writepage(struct page *page, struct writeback_control *wbc) int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; + struct nfs_pageio_descriptor pgio; int err; nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES); + nfs_pageio_init_write(&pgio, inode, wb_priority(wbc)); + wbc->fs_private = &pgio; err = generic_writepages(mapping, wbc); + nfs_pageio_complete(&pgio); if (err) return err; - err = nfs_flush_mapping(mapping, wbc, wb_priority(wbc)); - if (err < 0) - goto out; - nfs_add_stats(inode, NFSIOS_WRITEPAGES, err); - err = 0; -out: - return err; + if (pgio.pg_error) + return pgio.pg_error; + return 0; } /* @@ -503,11 +511,11 @@ int nfs_reschedule_unstable_write(struct nfs_page *req) * * Interruptible by signals only if mounted with intr flag. */ -static int nfs_wait_on_requests_locked(struct inode *inode, unsigned long idx_start, unsigned int npages) +static int nfs_wait_on_requests_locked(struct inode *inode, pgoff_t idx_start, unsigned int npages) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs_page *req; - unsigned long idx_end, next; + pgoff_t idx_end, next; unsigned int res = 0; int error; @@ -536,18 +544,6 @@ static int nfs_wait_on_requests_locked(struct inode *inode, unsigned long idx_st return res; } -static void nfs_cancel_dirty_list(struct list_head *head) -{ - struct nfs_page *req; - while(!list_empty(head)) { - req = nfs_list_entry(head->next); - nfs_list_remove_request(req); - nfs_end_page_writeback(req->wb_page); - nfs_inode_remove_request(req); - nfs_clear_page_writeback(req); - } -} - static void nfs_cancel_commit_list(struct list_head *head) { struct nfs_page *req; @@ -574,7 +570,7 @@ static void nfs_cancel_commit_list(struct list_head *head) * The requests are *not* checked to ensure that they form a contiguous set. */ static int -nfs_scan_commit(struct inode *inode, struct list_head *dst, unsigned long idx_start, unsigned int npages) +nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, unsigned int npages) { struct nfs_inode *nfsi = NFS_I(inode); int res = 0; @@ -588,40 +584,12 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst, unsigned long idx_st return res; } #else -static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst, unsigned long idx_start, unsigned int npages) +static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, unsigned int npages) { return 0; } #endif -static int nfs_wait_on_write_congestion(struct address_space *mapping) -{ - struct inode *inode = mapping->host; - struct backing_dev_info *bdi = mapping->backing_dev_info; - int ret = 0; - - might_sleep(); - - if (!bdi_write_congested(bdi)) - return 0; - - nfs_inc_stats(inode, NFSIOS_CONGESTIONWAIT); - - do { - struct rpc_clnt *clnt = NFS_CLIENT(inode); - sigset_t oldset; - - rpc_clnt_sigmask(clnt, &oldset); - ret = congestion_wait_interruptible(WRITE, HZ/10); - rpc_clnt_sigunmask(clnt, &oldset); - if (ret == -ERESTARTSYS) - break; - ret = 0; - } while (bdi_write_congested(bdi)); - - return ret; -} - /* * Try to update any existing write request, or create one if there is none. * In order to match, the request's credentials must match those of @@ -636,12 +604,10 @@ static struct nfs_page * nfs_update_request(struct nfs_open_context* ctx, struct inode *inode = mapping->host; struct nfs_inode *nfsi = NFS_I(inode); struct nfs_page *req, *new = NULL; - unsigned long rqend, end; + pgoff_t rqend, end; end = offset + bytes; - if (nfs_wait_on_write_congestion(mapping)) - return ERR_PTR(-ERESTARTSYS); for (;;) { /* Loop over all inode entries and see if we find * A request for the page we wish to update @@ -865,7 +831,7 @@ static void nfs_execute_write(struct nfs_write_data *data) * Generate multiple small requests to write out a single * contiguous dirty area on one page. */ -static int nfs_flush_multi(struct inode *inode, struct list_head *head, int how) +static int nfs_flush_multi(struct inode *inode, struct list_head *head, unsigned int npages, size_t count, int how) { struct nfs_page *req = nfs_list_entry(head->next); struct page *page = req->wb_page; @@ -877,11 +843,11 @@ static int nfs_flush_multi(struct inode *inode, struct list_head *head, int how) nfs_list_remove_request(req); - nbytes = req->wb_bytes; + nbytes = count; do { size_t len = min(nbytes, wsize); - data = nfs_writedata_alloc(len); + data = nfs_writedata_alloc(1); if (!data) goto out_bad; list_add(&data->pages, &list); @@ -892,23 +858,19 @@ static int nfs_flush_multi(struct inode *inode, struct list_head *head, int how) ClearPageError(page); offset = 0; - nbytes = req->wb_bytes; + nbytes = count; do { data = list_entry(list.next, struct nfs_write_data, pages); list_del_init(&data->pages); data->pagevec[0] = page; - if (nbytes > wsize) { - nfs_write_rpcsetup(req, data, &nfs_write_partial_ops, - wsize, offset, how); - offset += wsize; - nbytes -= wsize; - } else { - nfs_write_rpcsetup(req, data, &nfs_write_partial_ops, - nbytes, offset, how); - nbytes = 0; - } + if (nbytes < wsize) + wsize = nbytes; + nfs_write_rpcsetup(req, data, &nfs_write_partial_ops, + wsize, offset, how); + offset += wsize; + nbytes -= wsize; nfs_execute_write(data); } while (nbytes != 0); @@ -934,26 +896,23 @@ out_bad: * This is the case if nfs_updatepage detects a conflicting request * that has been written but not committed. */ -static int nfs_flush_one(struct inode *inode, struct list_head *head, int how) +static int nfs_flush_one(struct inode *inode, struct list_head *head, unsigned int npages, size_t count, int how) { struct nfs_page *req; struct page **pages; struct nfs_write_data *data; - unsigned int count; - data = nfs_writedata_alloc(NFS_SERVER(inode)->wsize); + data = nfs_writedata_alloc(npages); if (!data) goto out_bad; pages = data->pagevec; - count = 0; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); nfs_list_add_request(req, &data->pages); ClearPageError(req->wb_page); *pages++ = req->wb_page; - count += req->wb_bytes; } req = nfs_list_entry(data->pages.next); @@ -973,40 +932,15 @@ static int nfs_flush_one(struct inode *inode, struct list_head *head, int how) return -ENOMEM; } -static int nfs_flush_list(struct inode *inode, struct list_head *head, int npages, int how) +static void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, + struct inode *inode, int ioflags) { - LIST_HEAD(one_request); - int (*flush_one)(struct inode *, struct list_head *, int); - struct nfs_page *req; - int wpages = NFS_SERVER(inode)->wpages; int wsize = NFS_SERVER(inode)->wsize; - int error; - flush_one = nfs_flush_one; if (wsize < PAGE_CACHE_SIZE) - flush_one = nfs_flush_multi; - /* For single writes, FLUSH_STABLE is more efficient */ - if (npages <= wpages && npages == NFS_I(inode)->npages - && nfs_list_entry(head->next)->wb_bytes <= wsize) - how |= FLUSH_STABLE; - - do { - nfs_coalesce_requests(head, &one_request, wpages); - req = nfs_list_entry(one_request.next); - error = flush_one(inode, &one_request, how); - if (error < 0) - goto out_err; - } while (!list_empty(head)); - return 0; -out_err: - while (!list_empty(head)) { - req = nfs_list_entry(head->next); - nfs_list_remove_request(req); - nfs_redirty_request(req); - nfs_end_page_writeback(req->wb_page); - nfs_clear_page_writeback(req); - } - return error; + nfs_pageio_init(pgio, inode, nfs_flush_multi, wsize, ioflags); + else + nfs_pageio_init(pgio, inode, nfs_flush_one, wsize, ioflags); } /* @@ -1330,31 +1264,7 @@ static const struct rpc_call_ops nfs_commit_ops = { .rpc_call_done = nfs_commit_done, .rpc_release = nfs_commit_release, }; -#else -static inline int nfs_commit_list(struct inode *inode, struct list_head *head, int how) -{ - return 0; -} -#endif - -static long nfs_flush_mapping(struct address_space *mapping, struct writeback_control *wbc, int how) -{ - struct nfs_inode *nfsi = NFS_I(mapping->host); - LIST_HEAD(head); - long res; - - spin_lock(&nfsi->req_lock); - res = nfs_scan_dirty(mapping, wbc, &head); - spin_unlock(&nfsi->req_lock); - if (res) { - int error = nfs_flush_list(mapping->host, &head, res, how); - if (error < 0) - return error; - } - return res; -} -#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) int nfs_commit_inode(struct inode *inode, int how) { struct nfs_inode *nfsi = NFS_I(inode); @@ -1371,13 +1281,18 @@ int nfs_commit_inode(struct inode *inode, int how) } return res; } +#else +static inline int nfs_commit_list(struct inode *inode, struct list_head *head, int how) +{ + return 0; +} #endif long nfs_sync_mapping_wait(struct address_space *mapping, struct writeback_control *wbc, int how) { struct inode *inode = mapping->host; struct nfs_inode *nfsi = NFS_I(inode); - unsigned long idx_start, idx_end; + pgoff_t idx_start, idx_end; unsigned int npages = 0; LIST_HEAD(head); int nocommit = how & FLUSH_NOCOMMIT; @@ -1390,41 +1305,24 @@ long nfs_sync_mapping_wait(struct address_space *mapping, struct writeback_contr idx_start = wbc->range_start >> PAGE_CACHE_SHIFT; idx_end = wbc->range_end >> PAGE_CACHE_SHIFT; if (idx_end > idx_start) { - unsigned long l_npages = 1 + idx_end - idx_start; + pgoff_t l_npages = 1 + idx_end - idx_start; npages = l_npages; if (sizeof(npages) != sizeof(l_npages) && - (unsigned long)npages != l_npages) + (pgoff_t)npages != l_npages) npages = 0; } } how &= ~FLUSH_NOCOMMIT; spin_lock(&nfsi->req_lock); do { - wbc->pages_skipped = 0; ret = nfs_wait_on_requests_locked(inode, idx_start, npages); if (ret != 0) continue; - pages = nfs_scan_dirty(mapping, wbc, &head); - if (pages != 0) { - spin_unlock(&nfsi->req_lock); - if (how & FLUSH_INVALIDATE) { - nfs_cancel_dirty_list(&head); - ret = pages; - } else - ret = nfs_flush_list(inode, &head, pages, how); - spin_lock(&nfsi->req_lock); - continue; - } - if (wbc->pages_skipped != 0) - continue; if (nocommit) break; pages = nfs_scan_commit(inode, &head, idx_start, npages); - if (pages == 0) { - if (wbc->pages_skipped != 0) - continue; + if (pages == 0) break; - } if (how & FLUSH_INVALIDATE) { spin_unlock(&nfsi->req_lock); nfs_cancel_commit_list(&head); @@ -1456,7 +1354,7 @@ int nfs_wb_all(struct inode *inode) }; int ret; - ret = generic_writepages(mapping, &wbc); + ret = nfs_writepages(mapping, &wbc); if (ret < 0) goto out; ret = nfs_sync_mapping_wait(mapping, &wbc, 0); @@ -1479,11 +1377,9 @@ int nfs_sync_mapping_range(struct address_space *mapping, loff_t range_start, lo }; int ret; - if (!(how & FLUSH_NOWRITEPAGE)) { - ret = generic_writepages(mapping, &wbc); - if (ret < 0) - goto out; - } + ret = nfs_writepages(mapping, &wbc); + if (ret < 0) + goto out; ret = nfs_sync_mapping_wait(mapping, &wbc, how); if (ret >= 0) return 0; @@ -1506,7 +1402,7 @@ int nfs_wb_page_priority(struct inode *inode, struct page *page, int how) int ret; BUG_ON(!PageLocked(page)); - if (!(how & FLUSH_NOWRITEPAGE) && clear_page_dirty_for_io(page)) { + if (clear_page_dirty_for_io(page)) { ret = nfs_writepage_locked(page, &wbc); if (ret < 0) goto out; @@ -1531,10 +1427,18 @@ int nfs_wb_page(struct inode *inode, struct page* page) int nfs_set_page_dirty(struct page *page) { - spinlock_t *req_lock = &NFS_I(page->mapping->host)->req_lock; + struct address_space *mapping = page->mapping; + struct inode *inode; + spinlock_t *req_lock; struct nfs_page *req; int ret; + if (!mapping) + goto out_raced; + inode = mapping->host; + if (!inode) + goto out_raced; + req_lock = &NFS_I(inode)->req_lock; spin_lock(req_lock); req = nfs_page_find_request_locked(page); if (req != NULL) { @@ -1547,6 +1451,8 @@ int nfs_set_page_dirty(struct page *page) ret = __set_page_dirty_nobuffers(page); spin_unlock(req_lock); return ret; +out_raced: + return !TestSetPageDirty(page); } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index fb14d68..32ffea0 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -315,16 +315,13 @@ out: /* * RPC procedure tables */ -#ifndef MAX -# define MAX(a, b) (((a) > (b))? (a) : (b)) -#endif - #define PROC(proc, call, argtype, restype) \ [NFSPROC4_CLNT_##proc] = { \ .p_proc = NFSPROC4_CB_##call, \ .p_encode = (kxdrproc_t) nfs4_xdr_##argtype, \ .p_decode = (kxdrproc_t) nfs4_xdr_##restype, \ - .p_bufsiz = MAX(NFS4_##argtype##_sz,NFS4_##restype##_sz) << 2, \ + .p_arglen = NFS4_##argtype##_sz, \ + .p_replen = NFS4_##restype##_sz, \ .p_statidx = NFSPROC4_CB_##call, \ .p_name = #proc, \ } diff --git a/fs/ocfs2/cluster/masklog.c b/fs/ocfs2/cluster/masklog.c index 636593b..2e975c0 100644 --- a/fs/ocfs2/cluster/masklog.c +++ b/fs/ocfs2/cluster/masklog.c @@ -147,7 +147,7 @@ static struct kset mlog_kset = { .kobj = {.name = "logmask", .ktype = &mlog_ktype}, }; -int mlog_sys_init(struct subsystem *o2cb_subsys) +int mlog_sys_init(struct kset *o2cb_subsys) { int i = 0; @@ -157,7 +157,7 @@ int mlog_sys_init(struct subsystem *o2cb_subsys) } mlog_attr_ptrs[i] = NULL; - mlog_kset.subsys = o2cb_subsys; + kobj_set_kset_s(&mlog_kset, o2cb_subsys); return kset_register(&mlog_kset); } diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h index a42628b..75cd877 100644 --- a/fs/ocfs2/cluster/masklog.h +++ b/fs/ocfs2/cluster/masklog.h @@ -278,7 +278,7 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits; #include <linux/kobject.h> #include <linux/sysfs.h> -int mlog_sys_init(struct subsystem *o2cb_subsys); +int mlog_sys_init(struct kset *o2cb_subsys); void mlog_sys_shutdown(void); #endif /* O2CLUSTER_MASKLOG_H */ diff --git a/fs/ocfs2/cluster/sys.c b/fs/ocfs2/cluster/sys.c index 1d9f6ac..64f6f37 100644 --- a/fs/ocfs2/cluster/sys.c +++ b/fs/ocfs2/cluster/sys.c @@ -42,7 +42,6 @@ struct o2cb_attribute { #define O2CB_ATTR(_name, _mode, _show, _store) \ struct o2cb_attribute o2cb_attr_##_name = __ATTR(_name, _mode, _show, _store) -#define to_o2cb_subsys(k) container_of(to_kset(k), struct subsystem, kset) #define to_o2cb_attr(_attr) container_of(_attr, struct o2cb_attribute, attr) static ssize_t o2cb_interface_revision_show(char *buf) @@ -79,7 +78,7 @@ static ssize_t o2cb_show(struct kobject * kobj, struct attribute * attr, char * buffer) { struct o2cb_attribute *o2cb_attr = to_o2cb_attr(attr); - struct subsystem *sbs = to_o2cb_subsys(kobj); + struct kset *sbs = to_kset(kobj); BUG_ON(sbs != &o2cb_subsys); @@ -93,7 +92,7 @@ o2cb_store(struct kobject * kobj, struct attribute * attr, const char * buffer, size_t count) { struct o2cb_attribute *o2cb_attr = to_o2cb_attr(attr); - struct subsystem *sbs = to_o2cb_subsys(kobj); + struct kset *sbs = to_kset(kobj); BUG_ON(sbs != &o2cb_subsys); @@ -112,7 +111,7 @@ int o2cb_sys_init(void) { int ret; - o2cb_subsys.kset.kobj.ktype = &o2cb_subsys_type; + o2cb_subsys.kobj.ktype = &o2cb_subsys_type; ret = subsystem_register(&o2cb_subsys); if (ret) return ret; diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 8a7d003..f01572f 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -312,7 +312,7 @@ static struct attribute * default_attrs[] = { NULL, }; -extern struct subsystem block_subsys; +extern struct kset block_subsys; static void part_release(struct kobject *kobj) { @@ -388,7 +388,7 @@ void add_partition(struct gendisk *disk, int part, sector_t start, sector_t len, kobject_add(&p->kobj); if (!disk->part_uevent_suppress) kobject_uevent(&p->kobj, KOBJ_ADD); - sysfs_create_link(&p->kobj, &block_subsys.kset.kobj, "subsystem"); + sysfs_create_link(&p->kobj, &block_subsys.kobj, "subsystem"); if (flags & ADDPART_FLAG_WHOLEDISK) { static struct attribute addpartattr = { .name = "whole_disk", @@ -444,7 +444,7 @@ static int disk_sysfs_symlinks(struct gendisk *disk) goto err_out_dev_link; } - err = sysfs_create_link(&disk->kobj, &block_subsys.kset.kobj, + err = sysfs_create_link(&disk->kobj, &block_subsys.kobj, "subsystem"); if (err) goto err_out_disk_name_lnk; diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index c8178b7..2cac562 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -68,7 +68,7 @@ static struct dentry *get_xa_root(struct super_block *sb, int flags) if (!privroot) return ERR_PTR(-ENODATA); - mutex_lock(&privroot->d_inode->i_mutex); + mutex_lock_nested(&privroot->d_inode->i_mutex, I_MUTEX_XATTR); if (REISERFS_SB(sb)->xattr_root) { xaroot = dget(REISERFS_SB(sb)->xattr_root); goto out; diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c index 8ea2a51..d3b9f5f 100644 --- a/fs/sysfs/bin.c +++ b/fs/sysfs/bin.c @@ -59,7 +59,7 @@ read(struct file * file, char __user * userbuf, size_t count, loff_t * off) if (copy_to_user(userbuf, buffer, count)) return -EFAULT; - pr_debug("offs = %lld, *off = %lld, count = %d\n", offs, *off, count); + pr_debug("offs = %lld, *off = %lld, count = %zd\n", offs, *off, count); *off = offs + count; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index db0413a..0e637ad 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -13,8 +13,7 @@ #include "sysfs.h" -#define to_subsys(k) container_of(k,struct subsystem,kset.kobj) -#define to_sattr(a) container_of(a,struct subsys_attribute,attr) +#define to_sattr(a) container_of(a,struct subsys_attribute, attr) /* * Subsystem file operations. @@ -24,12 +23,12 @@ static ssize_t subsys_attr_show(struct kobject * kobj, struct attribute * attr, char * page) { - struct subsystem * s = to_subsys(kobj); + struct kset *kset = to_kset(kobj); struct subsys_attribute * sattr = to_sattr(attr); ssize_t ret = -EIO; if (sattr->show) - ret = sattr->show(s,page); + ret = sattr->show(kset, page); return ret; } @@ -37,12 +36,12 @@ static ssize_t subsys_attr_store(struct kobject * kobj, struct attribute * attr, const char * page, size_t count) { - struct subsystem * s = to_subsys(kobj); + struct kset *kset = to_kset(kobj); struct subsys_attribute * sattr = to_sattr(attr); ssize_t ret = -EIO; if (sattr->store) - ret = sattr->store(s,page,count); + ret = sattr->store(kset, page, count); return ret; } |