From b55e0ba19cd2d83317a7f1dbb626080951442ab3 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 28 Apr 2008 18:22:50 -0400 Subject: [PATCH 01/51] nfsd: remove unnecessary atomic ops These bit operations don't need to be atomic. They're all done under a single big mutex anyway. Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 8799b8708188..5c97d47676ae 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1579,8 +1579,8 @@ nfs4_upgrade_open(struct svc_rqst *rqstp, struct svc_fh *cur_fh, struct nfs4_sta } /* remember the open */ filp->f_mode |= open->op_share_access; - set_bit(open->op_share_access, &stp->st_access_bmap); - set_bit(open->op_share_deny, &stp->st_deny_bmap); + __set_bit(open->op_share_access, &stp->st_access_bmap); + __set_bit(open->op_share_deny, &stp->st_deny_bmap); return nfs_ok; } From 3b12cd9862d5f560031d90bda78952ab55e36b24 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 5 May 2008 17:17:44 -0400 Subject: [PATCH 02/51] nfsd: add dprintk of compound return We already print each operation of the compound when debugging is turned on; printing the result could also help with remote debugging. Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index c309c881bd4e..313484380a9b 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -952,6 +952,7 @@ encode_op: out: nfsd4_release_compoundargs(args); cstate_free(cstate); + dprintk("nfsv4 compound returned %d\n", ntohl(status)); return status; } From 13b1867cacbfe6d8203f432996bd8a2ee6b04e79 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Thu, 29 May 2008 12:56:08 +0300 Subject: [PATCH 03/51] nfsd: make nfs4xdr WRITEMEM safe against zero count WRITEMEM zeroes the last word in the destination buffer for padding purposes, but this must not be done if no bytes are to be copied, as it would result in zeroing of the word right before the array. The current implementation works since it's always called with non zero nbytes or it follows an encoding of the string (or opaque) length which, if equal to zero, can be overwritten with zero. Nevertheless, it seems safer to check for this case. Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index c513bbdf2d36..9547ab636274 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1201,7 +1201,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) *p++ = htonl((u32)((n) >> 32)); \ *p++ = htonl((u32)(n)); \ } while (0) -#define WRITEMEM(ptr,nbytes) do { \ +#define WRITEMEM(ptr,nbytes) do if (nbytes > 0) { \ *(p + XDR_QUADLEN(nbytes) -1) = 0; \ memcpy(p, ptr, nbytes); \ p += XDR_QUADLEN(nbytes); \ From 7c11337d9d81cde0a08a0da63cbfb20653890fa1 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Wed, 4 Jun 2008 18:50:06 -0400 Subject: [PATCH 04/51] nfsd: remove three unused NFS4_ACE_* defines These flag bits aren't used by either the protocol or our implementation, so I don't know why they were here. Thanks to Johann Dahm for running across these. Signed-off-by: J. Bruce Fields Cc: Johann Dahm --- include/linux/nfs4.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 8726491de154..ea0366769484 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -65,9 +65,6 @@ #define NFS4_ACE_SUCCESSFUL_ACCESS_ACE_FLAG 0x00000010 #define NFS4_ACE_FAILED_ACCESS_ACE_FLAG 0x00000020 #define NFS4_ACE_IDENTIFIER_GROUP 0x00000040 -#define NFS4_ACE_OWNER 0x00000080 -#define NFS4_ACE_GROUP 0x00000100 -#define NFS4_ACE_EVERYONE 0x00000200 #define NFS4_ACE_READ_DATA 0x00000001 #define NFS4_ACE_LIST_DIRECTORY 0x00000001 From a5e561fee651eb03086ca21e9aa78e1fffa4581a Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Tue, 10 Jun 2008 12:59:07 +0300 Subject: [PATCH 05/51] nfsd: eliminate unused nfs4_callback.cb_program The cb_program member of struct nfs4_callback unused since commit ff7d9756 nfsd: use static memory for callback program and stats Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/state.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index db348f749376..06e9686d9dea 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -98,7 +98,6 @@ struct nfs4_callback { u32 cb_ident; /* RPC client info */ atomic_t cb_set; /* successful CB_NULL call */ - struct rpc_program cb_program; struct rpc_stat cb_stat; struct rpc_clnt * cb_client; }; From 0d169ca136357d51a65d686f3c84866a8ba20ae9 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Tue, 10 Jun 2008 13:39:43 +0300 Subject: [PATCH 06/51] nfsd: eliminate unused nfs4_callback.cb_stat The cb_stat member of struct nfs4_callback is unused since commit ff7d9756 nfsd: use static memory for callback program and stats Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- include/linux/nfsd/state.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h index 06e9686d9dea..d0fe2e378452 100644 --- a/include/linux/nfsd/state.h +++ b/include/linux/nfsd/state.h @@ -98,7 +98,6 @@ struct nfs4_callback { u32 cb_ident; /* RPC client info */ atomic_t cb_set; /* successful CB_NULL call */ - struct rpc_stat cb_stat; struct rpc_clnt * cb_client; }; From bedbdd8bada194a690d2901801bf8451965086b3 Mon Sep 17 00:00:00 2001 From: Neil Brown Date: Tue, 10 Jun 2008 08:40:35 -0400 Subject: [PATCH 07/51] knfsd: Replace lock_kernel with a mutex for nfsd thread startup/shutdown locking. This removes the BKL from the RPC service creation codepath. The BKL really isn't adequate for this job since some of this info needs protection across sleeps. Also, add some comments to try and clarify how the locking should work and to make it clear that the BKL isn't necessary as long as there is adequate locking between tasks when touching the svc_serv fields. Signed-off-by: Neil Brown Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfsctl.c | 37 ++++++++++++++++++++------------ fs/nfsd/nfssvc.c | 45 ++++++++++++++++++++++++++++----------- include/linux/nfsd/nfsd.h | 1 + net/sunrpc/svc.c | 15 +++++++------ 4 files changed, 65 insertions(+), 33 deletions(-) diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 5ac00c4fee91..049d2a9c7715 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -450,22 +450,26 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size) int i; int rv; int len; - int npools = nfsd_nrpools(); + int npools; int *nthreads; + mutex_lock(&nfsd_mutex); + npools = nfsd_nrpools(); if (npools == 0) { /* * NFS is shut down. The admin can start it by * writing to the threads file but NOT the pool_threads * file, sorry. Report zero threads. */ + mutex_unlock(&nfsd_mutex); strcpy(buf, "0\n"); return strlen(buf); } nthreads = kcalloc(npools, sizeof(int), GFP_KERNEL); + rv = -ENOMEM; if (nthreads == NULL) - return -ENOMEM; + goto out_free; if (size > 0) { for (i = 0; i < npools; i++) { @@ -496,10 +500,12 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size) mesg += len; } + mutex_unlock(&nfsd_mutex); return (mesg-buf); out_free: kfree(nthreads); + mutex_unlock(&nfsd_mutex); return rv; } @@ -566,14 +572,13 @@ static ssize_t write_versions(struct file *file, char *buf, size_t size) return len; } -static ssize_t write_ports(struct file *file, char *buf, size_t size) +static ssize_t __write_ports(struct file *file, char *buf, size_t size) { if (size == 0) { int len = 0; - lock_kernel(); + if (nfsd_serv) len = svc_xprt_names(nfsd_serv, buf, 0); - unlock_kernel(); return len; } /* Either a single 'fd' number is written, in which @@ -603,9 +608,7 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size) /* Decrease the count, but don't shutdown the * the service */ - lock_kernel(); nfsd_serv->sv_nrthreads--; - unlock_kernel(); } return err < 0 ? err : 0; } @@ -614,10 +617,8 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size) int len = 0; if (!toclose) return -ENOMEM; - lock_kernel(); if (nfsd_serv) len = svc_sock_names(buf, nfsd_serv, toclose); - unlock_kernel(); if (len >= 0) lockd_down(); kfree(toclose); @@ -655,7 +656,6 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size) if (sscanf(&buf[1], "%15s %4d", transport, &port) == 2) { if (port == 0) return -EINVAL; - lock_kernel(); if (nfsd_serv) { xprt = svc_find_xprt(nfsd_serv, transport, AF_UNSPEC, port); @@ -666,13 +666,22 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size) } else err = -ENOTCONN; } - unlock_kernel(); return err < 0 ? err : 0; } } return -EINVAL; } +static ssize_t write_ports(struct file *file, char *buf, size_t size) +{ + ssize_t rv; + mutex_lock(&nfsd_mutex); + rv = __write_ports(file, buf, size); + mutex_unlock(&nfsd_mutex); + return rv; +} + + int nfsd_max_blksize; static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) @@ -691,13 +700,13 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) if (bsize > NFSSVC_MAXBLKSIZE) bsize = NFSSVC_MAXBLKSIZE; bsize &= ~(1024-1); - lock_kernel(); + mutex_lock(&nfsd_mutex); if (nfsd_serv && nfsd_serv->sv_nrthreads) { - unlock_kernel(); + mutex_unlock(&nfsd_mutex); return -EBUSY; } nfsd_max_blksize = bsize; - unlock_kernel(); + mutex_unlock(&nfsd_mutex); } return sprintf(buf, "%d\n", nfsd_max_blksize); } diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 941041f4b136..512bd04c6dda 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -53,11 +53,27 @@ extern struct svc_program nfsd_program; static void nfsd(struct svc_rqst *rqstp); struct timeval nfssvc_boot; - struct svc_serv *nfsd_serv; static atomic_t nfsd_busy; static unsigned long nfsd_last_call; static DEFINE_SPINLOCK(nfsd_call_lock); +/* + * nfsd_mutex protects nfsd_serv -- both the pointer itself and the members + * of the svc_serv struct. In particular, ->sv_nrthreads but also to some + * extent ->sv_temp_socks and ->sv_permsocks. It also protects nfsdstats.th_cnt + * + * If (out side the lock) nfsd_serv is non-NULL, then it must point to a + * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0. That number + * of nfsd threads must exist and each must listed in ->sp_all_threads in each + * entry of ->sv_pools[]. + * + * Transitions of the thread count between zero and non-zero are of particular + * interest since the svc_serv needs to be created and initialized at that + * point, or freed. + */ +DEFINE_MUTEX(nfsd_mutex); +struct svc_serv *nfsd_serv; + #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static struct svc_stat nfsd_acl_svcstats; static struct svc_version * nfsd_acl_version[] = { @@ -190,13 +206,14 @@ void nfsd_reset_versions(void) } } + int nfsd_create_serv(void) { int err = 0; - lock_kernel(); + + WARN_ON(!mutex_is_locked(&nfsd_mutex)); if (nfsd_serv) { svc_get(nfsd_serv); - unlock_kernel(); return 0; } if (nfsd_max_blksize == 0) { @@ -223,7 +240,7 @@ int nfsd_create_serv(void) nfsd, SIG_NOCLEAN, THIS_MODULE); if (nfsd_serv == NULL) err = -ENOMEM; - unlock_kernel(); + do_gettimeofday(&nfssvc_boot); /* record boot time */ return err; } @@ -282,6 +299,8 @@ int nfsd_set_nrthreads(int n, int *nthreads) int tot = 0; int err = 0; + WARN_ON(!mutex_is_locked(&nfsd_mutex)); + if (nfsd_serv == NULL || n <= 0) return 0; @@ -316,7 +335,6 @@ int nfsd_set_nrthreads(int n, int *nthreads) nthreads[0] = 1; /* apply the new numbers */ - lock_kernel(); svc_get(nfsd_serv); for (i = 0; i < n; i++) { err = svc_set_num_threads(nfsd_serv, &nfsd_serv->sv_pools[i], @@ -325,7 +343,6 @@ int nfsd_set_nrthreads(int n, int *nthreads) break; } svc_destroy(nfsd_serv); - unlock_kernel(); return err; } @@ -334,8 +351,8 @@ int nfsd_svc(unsigned short port, int nrservs) { int error; - - lock_kernel(); + + mutex_lock(&nfsd_mutex); dprintk("nfsd: creating service\n"); error = -EINVAL; if (nrservs <= 0) @@ -363,7 +380,7 @@ nfsd_svc(unsigned short port, int nrservs) failure: svc_destroy(nfsd_serv); /* Release server */ out: - unlock_kernel(); + mutex_unlock(&nfsd_mutex); return error; } @@ -399,7 +416,7 @@ nfsd(struct svc_rqst *rqstp) sigset_t shutdown_mask, allowed_mask; /* Lock module and set up kernel thread */ - lock_kernel(); + mutex_lock(&nfsd_mutex); daemonize("nfsd"); /* After daemonize() this kernel thread shares current->fs @@ -417,11 +434,13 @@ nfsd(struct svc_rqst *rqstp) siginitsetinv(&shutdown_mask, SHUTDOWN_SIGS); siginitsetinv(&allowed_mask, ALLOWED_SIGS); + nfsdstats.th_cnt++; rqstp->rq_task = current; - unlock_kernel(); + mutex_unlock(&nfsd_mutex); + /* * We want less throttling in balance_dirty_pages() so that nfs to @@ -477,7 +496,7 @@ nfsd(struct svc_rqst *rqstp) /* Clear signals before calling svc_exit_thread() */ flush_signals(current); - lock_kernel(); + mutex_lock(&nfsd_mutex); nfsdstats.th_cnt --; @@ -486,7 +505,7 @@ out: svc_exit_thread(rqstp); /* Release module */ - unlock_kernel(); + mutex_unlock(&nfsd_mutex); module_put_and_exit(0); } diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 41d30c9c9de6..88d85b964429 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -54,6 +54,7 @@ typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int); extern struct svc_program nfsd_program; extern struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; +extern struct mutex nfsd_mutex; extern struct svc_serv *nfsd_serv; extern struct seq_operations nfs_exports_op; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 01c7e311b904..7bffaff2a3ab 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -461,7 +461,8 @@ svc_create_pooled(struct svc_program *prog, unsigned int bufsize, EXPORT_SYMBOL(svc_create_pooled); /* - * Destroy an RPC service. Should be called with the BKL held + * Destroy an RPC service. Should be called with appropriate locking to + * protect the sv_nrthreads, sv_permsocks and sv_tempsocks. */ void svc_destroy(struct svc_serv *serv) @@ -578,9 +579,10 @@ out_enomem: EXPORT_SYMBOL(svc_prepare_thread); /* - * Create a thread in the given pool. Caller must hold BKL. - * On a NUMA or SMP machine, with a multi-pool serv, the thread - * will be restricted to run on the cpus belonging to the pool. + * Create a thread in the given pool. Caller must hold BKL or another lock to + * serialize access to the svc_serv struct. On a NUMA or SMP machine, with a + * multi-pool serv, the thread will be restricted to run on the cpus belonging + * to the pool. */ static int __svc_create_thread(svc_thread_fn func, struct svc_serv *serv, @@ -674,7 +676,7 @@ found_pool: * of threads the given number. If `pool' is non-NULL, applies * only to threads in that pool, otherwise round-robins between * all pools. Must be called with a svc_get() reference and - * the BKL held. + * the BKL or another lock to protect access to svc_serv fields. * * Destroying threads relies on the service threads filling in * rqstp->rq_task, which only the nfs ones do. Assumes the serv @@ -722,7 +724,8 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) EXPORT_SYMBOL(svc_set_num_threads); /* - * Called from a server thread as it's exiting. Caller must hold BKL. + * Called from a server thread as it's exiting. Caller must hold the BKL or + * the "service mutex", whichever is appropriate for the service. */ void svc_exit_thread(struct svc_rqst *rqstp) From 3dd98a3bccb1bdd30b8a4a755e7bead1b64160ec Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 10 Jun 2008 08:40:36 -0400 Subject: [PATCH 08/51] knfsd: clean up nfsd filesystem interfaces Several of the nfsd filesystem interfaces allow changes to parameters that don't have any effect on a running nfsd service. They are only ever checked when nfsd is started. This patch fixes it so that changes to those procfiles return -EBUSY if nfsd is already running to make it clear that changes on the fly don't work. The patch should also close some relatively harmless races between changing the info in those interfaces and starting nfsd, since these variables are being moved under the protection of the nfsd_mutex. Finally, the nfsv4recoverydir file always returns -EINVAL if read. This patch fixes it to return the recoverydir path as expected. Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 17 +++++++++--- fs/nfsd/nfsctl.c | 66 ++++++++++++++++++++++++++++++++++++--------- fs/nfsd/nfssvc.c | 8 ++++++ 3 files changed, 74 insertions(+), 17 deletions(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 5c97d47676ae..bf11d6879ab4 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3249,12 +3249,14 @@ nfs4_state_shutdown(void) nfs4_unlock_state(); } +/* + * user_recovery_dirname is protected by the nfsd_mutex since it's only + * accessed when nfsd is starting. + */ static void nfs4_set_recdir(char *recdir) { - nfs4_lock_state(); strcpy(user_recovery_dirname, recdir); - nfs4_unlock_state(); } /* @@ -3278,6 +3280,12 @@ nfs4_reset_recoverydir(char *recdir) return status; } +char * +nfs4_recoverydir(void) +{ + return user_recovery_dirname; +} + /* * Called when leasetime is changed. * @@ -3286,11 +3294,12 @@ nfs4_reset_recoverydir(char *recdir) * we start to register any changes in lease time. If the administrator * really wants to change the lease time *now*, they can go ahead and bring * nfsd down and then back up again after changing the lease time. + * + * user_lease_time is protected by nfsd_mutex since it's only really accessed + * when nfsd is starting */ void nfs4_reset_lease(time_t leasetime) { - lock_kernel(); user_lease_time = leasetime; - unlock_kernel(); } diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 049d2a9c7715..2c2eb8796c10 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -509,7 +509,7 @@ out_free: return rv; } -static ssize_t write_versions(struct file *file, char *buf, size_t size) +static ssize_t __write_versions(struct file *file, char *buf, size_t size) { /* * Format: @@ -572,6 +572,16 @@ static ssize_t write_versions(struct file *file, char *buf, size_t size) return len; } +static ssize_t write_versions(struct file *file, char *buf, size_t size) +{ + ssize_t rv; + + mutex_lock(&nfsd_mutex); + rv = __write_versions(file, buf, size); + mutex_unlock(&nfsd_mutex); + return rv; +} + static ssize_t __write_ports(struct file *file, char *buf, size_t size) { if (size == 0) { @@ -675,6 +685,7 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size) static ssize_t write_ports(struct file *file, char *buf, size_t size) { ssize_t rv; + mutex_lock(&nfsd_mutex); rv = __write_ports(file, buf, size); mutex_unlock(&nfsd_mutex); @@ -714,16 +725,17 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) #ifdef CONFIG_NFSD_V4 extern time_t nfs4_leasetime(void); -static ssize_t write_leasetime(struct file *file, char *buf, size_t size) +static ssize_t __write_leasetime(struct file *file, char *buf, size_t size) { /* if size > 10 seconds, call * nfs4_reset_lease() then write out the new lease (seconds) as reply */ char *mesg = buf; - int rv; + int rv, lease; if (size > 0) { - int lease; + if (nfsd_serv) + return -EBUSY; rv = get_int(&mesg, &lease); if (rv) return rv; @@ -735,24 +747,52 @@ static ssize_t write_leasetime(struct file *file, char *buf, size_t size) return strlen(buf); } -static ssize_t write_recoverydir(struct file *file, char *buf, size_t size) +static ssize_t write_leasetime(struct file *file, char *buf, size_t size) +{ + ssize_t rv; + + mutex_lock(&nfsd_mutex); + rv = __write_leasetime(file, buf, size); + mutex_unlock(&nfsd_mutex); + return rv; +} + +extern char *nfs4_recoverydir(void); + +static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size) { char *mesg = buf; char *recdir; int len, status; - if (size == 0 || size > PATH_MAX || buf[size-1] != '\n') - return -EINVAL; - buf[size-1] = 0; + if (size > 0) { + if (nfsd_serv) + return -EBUSY; + if (size > PATH_MAX || buf[size-1] != '\n') + return -EINVAL; + buf[size-1] = 0; - recdir = mesg; - len = qword_get(&mesg, recdir, size); - if (len <= 0) - return -EINVAL; + recdir = mesg; + len = qword_get(&mesg, recdir, size); + if (len <= 0) + return -EINVAL; - status = nfs4_reset_recoverydir(recdir); + status = nfs4_reset_recoverydir(recdir); + } + sprintf(buf, "%s\n", nfs4_recoverydir()); return strlen(buf); } + +static ssize_t write_recoverydir(struct file *file, char *buf, size_t size) +{ + ssize_t rv; + + mutex_lock(&nfsd_mutex); + rv = __write_recoverydir(file, buf, size); + mutex_unlock(&nfsd_mutex); + return rv; +} + #endif /*----------------------------------------------------------------------------*/ diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 512bd04c6dda..929af233510e 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -70,6 +70,14 @@ static DEFINE_SPINLOCK(nfsd_call_lock); * Transitions of the thread count between zero and non-zero are of particular * interest since the svc_serv needs to be created and initialized at that * point, or freed. + * + * Finally, the nfsd_mutex also protects some of the global variables that are + * accessed when nfsd starts and that are settable via the write_* routines in + * nfsctl.c. In particular: + * + * user_recovery_dirname + * user_lease_time + * nfsd_versions */ DEFINE_MUTEX(nfsd_mutex); struct svc_serv *nfsd_serv; From e096bbc6488d3e49d476bf986d33752709361277 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 10 Jun 2008 08:40:37 -0400 Subject: [PATCH 09/51] knfsd: remove special handling for SIGHUP The special handling for SIGHUP in knfsd is a holdover from much earlier versions of Linux where reloading the export table was more expensive. That facility is not really needed anymore and to my knowledge, is seldom-used. Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfssvc.c | 31 +++++++------------------------ 1 file changed, 7 insertions(+), 24 deletions(-) diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 929af233510e..6339cb70a08d 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -44,11 +44,6 @@ * when not handling a request. i.e. when waiting */ #define SHUTDOWN_SIGS (sigmask(SIGKILL) | sigmask(SIGHUP) | sigmask(SIGINT) | sigmask(SIGQUIT)) -/* if the last thread dies with SIGHUP, then the exports table is - * left unchanged ( like 2.4-{0-9} ). Any other signal will clear - * the exports table (like 2.2). - */ -#define SIG_NOCLEAN SIGHUP extern struct svc_program nfsd_program; static void nfsd(struct svc_rqst *rqstp); @@ -175,7 +170,6 @@ int nfsd_nrthreads(void) return nfsd_serv->sv_nrthreads; } -static int killsig; /* signal that was used to kill last nfsd */ static void nfsd_last_thread(struct svc_serv *serv) { /* When last nfsd thread exits we need to do some clean-up */ @@ -186,11 +180,9 @@ static void nfsd_last_thread(struct svc_serv *serv) nfsd_racache_shutdown(); nfs4_state_shutdown(); - printk(KERN_WARNING "nfsd: last server has exited\n"); - if (killsig != SIG_NOCLEAN) { - printk(KERN_WARNING "nfsd: unexporting all filesystems\n"); - nfsd_export_flush(); - } + printk(KERN_WARNING "nfsd: last server has exited, flushing export " + "cache\n"); + nfsd_export_flush(); } void nfsd_reset_versions(void) @@ -242,10 +234,9 @@ int nfsd_create_serv(void) } atomic_set(&nfsd_busy, 0); - nfsd_serv = svc_create_pooled(&nfsd_program, - nfsd_max_blksize, - nfsd_last_thread, - nfsd, SIG_NOCLEAN, THIS_MODULE); + nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize, + nfsd_last_thread, nfsd, SIGINT, + THIS_MODULE); if (nfsd_serv == NULL) err = -ENOMEM; @@ -490,17 +481,9 @@ nfsd(struct svc_rqst *rqstp) atomic_dec(&nfsd_busy); } - if (err != -EINTR) { + if (err != -EINTR) printk(KERN_WARNING "nfsd: terminating on error %d\n", -err); - } else { - unsigned int signo; - for (signo = 1; signo <= _NSIG; signo++) - if (sigismember(¤t->pending.signal, signo) && - !sigismember(¤t->blocked, signo)) - break; - killsig = signo; - } /* Clear signals before calling svc_exit_thread() */ flush_signals(current); From 9867d76ca16b3f455f9ca83861f4ce5c94a25928 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 10 Jun 2008 08:40:38 -0400 Subject: [PATCH 10/51] knfsd: convert knfsd to kthread API This patch is rather large, but I couldn't figure out a way to break it up that would remain bisectable. It does several things: - change svc_thread_fn typedef to better match what kthread_create expects - change svc_pool_map_set_cpumask to be more kthread friendly. Make it take a task arg and and get rid of the "oldmask" - have svc_set_num_threads call kthread_create directly - eliminate __svc_create_thread Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfssvc.c | 45 ++++++++++------ include/linux/sunrpc/svc.h | 2 +- net/sunrpc/svc.c | 104 +++++++++++++------------------------ 3 files changed, 66 insertions(+), 85 deletions(-) diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 6339cb70a08d..9e2156813710 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -46,7 +47,7 @@ #define SHUTDOWN_SIGS (sigmask(SIGKILL) | sigmask(SIGHUP) | sigmask(SIGINT) | sigmask(SIGQUIT)) extern struct svc_program nfsd_program; -static void nfsd(struct svc_rqst *rqstp); +static int nfsd(void *vrqstp); struct timeval nfssvc_boot; static atomic_t nfsd_busy; static unsigned long nfsd_last_call; @@ -407,18 +408,19 @@ update_thread_usage(int busy_threads) /* * This is the NFS server kernel thread */ -static void -nfsd(struct svc_rqst *rqstp) +static int +nfsd(void *vrqstp) { + struct svc_rqst *rqstp = (struct svc_rqst *) vrqstp; struct fs_struct *fsp; - int err; sigset_t shutdown_mask, allowed_mask; + int err, preverr = 0; + unsigned int signo; /* Lock module and set up kernel thread */ mutex_lock(&nfsd_mutex); - daemonize("nfsd"); - /* After daemonize() this kernel thread shares current->fs + /* At this point, the thread shares current->fs * with the init process. We need to create files with a * umask of 0 instead of init's umask. */ fsp = copy_fs_struct(current->fs); @@ -433,14 +435,18 @@ nfsd(struct svc_rqst *rqstp) siginitsetinv(&shutdown_mask, SHUTDOWN_SIGS); siginitsetinv(&allowed_mask, ALLOWED_SIGS); + /* + * thread is spawned with all signals set to SIG_IGN, re-enable + * the ones that matter + */ + for (signo = 1; signo <= _NSIG; signo++) { + if (!sigismember(&shutdown_mask, signo)) + allow_signal(signo); + } nfsdstats.th_cnt++; - - rqstp->rq_task = current; - mutex_unlock(&nfsd_mutex); - /* * We want less throttling in balance_dirty_pages() so that nfs to * localhost doesn't cause nfsd to lock up due to all the client's @@ -462,15 +468,25 @@ nfsd(struct svc_rqst *rqstp) */ while ((err = svc_recv(rqstp, 60*60*HZ)) == -EAGAIN) ; - if (err < 0) + if (err == -EINTR) break; + else if (err < 0) { + if (err != preverr) { + printk(KERN_WARNING "%s: unexpected error " + "from svc_recv (%d)\n", __func__, -err); + preverr = err; + } + schedule_timeout_uninterruptible(HZ); + continue; + } + update_thread_usage(atomic_read(&nfsd_busy)); atomic_inc(&nfsd_busy); /* Lock the export hash tables for reading. */ exp_readlock(); - /* Process request with signals blocked. */ + /* Process request with signals blocked. */ sigprocmask(SIG_SETMASK, &allowed_mask, NULL); svc_process(rqstp); @@ -481,14 +497,10 @@ nfsd(struct svc_rqst *rqstp) atomic_dec(&nfsd_busy); } - if (err != -EINTR) - printk(KERN_WARNING "nfsd: terminating on error %d\n", -err); - /* Clear signals before calling svc_exit_thread() */ flush_signals(current); mutex_lock(&nfsd_mutex); - nfsdstats.th_cnt --; out: @@ -498,6 +510,7 @@ out: /* Release module */ mutex_unlock(&nfsd_mutex); module_put_and_exit(0); + return 0; } static __be32 map_new_errors(u32 vers, __be32 nfserr) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 4b54c5fdcfd9..011d6d8100d8 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -22,7 +22,7 @@ /* * This is the RPC server thread function prototype */ -typedef void (*svc_thread_fn)(struct svc_rqst *); +typedef int (*svc_thread_fn)(void *); /* * diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 7bffaff2a3ab..03a9f1a9e75c 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -291,15 +292,14 @@ svc_pool_map_put(void) /* - * Set the current thread's cpus_allowed mask so that it + * Set the given thread's cpus_allowed mask so that it * will only run on cpus in the given pool. - * - * Returns 1 and fills in oldmask iff a cpumask was applied. */ -static inline int -svc_pool_map_set_cpumask(unsigned int pidx, cpumask_t *oldmask) +static inline void +svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx) { struct svc_pool_map *m = &svc_pool_map; + unsigned int node = m->pool_to[pidx]; /* * The caller checks for sv_nrpools > 1, which @@ -307,26 +307,17 @@ svc_pool_map_set_cpumask(unsigned int pidx, cpumask_t *oldmask) */ BUG_ON(m->count == 0); - switch (m->mode) - { - default: - return 0; + switch (m->mode) { case SVC_POOL_PERCPU: { - unsigned int cpu = m->pool_to[pidx]; - - *oldmask = current->cpus_allowed; - set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); - return 1; + set_cpus_allowed_ptr(task, &cpumask_of_cpu(node)); + break; } case SVC_POOL_PERNODE: { - unsigned int node = m->pool_to[pidx]; node_to_cpumask_ptr(nodecpumask, node); - - *oldmask = current->cpus_allowed; - set_cpus_allowed_ptr(current, nodecpumask); - return 1; + set_cpus_allowed_ptr(task, nodecpumask); + break; } } } @@ -578,47 +569,6 @@ out_enomem: } EXPORT_SYMBOL(svc_prepare_thread); -/* - * Create a thread in the given pool. Caller must hold BKL or another lock to - * serialize access to the svc_serv struct. On a NUMA or SMP machine, with a - * multi-pool serv, the thread will be restricted to run on the cpus belonging - * to the pool. - */ -static int -__svc_create_thread(svc_thread_fn func, struct svc_serv *serv, - struct svc_pool *pool) -{ - struct svc_rqst *rqstp; - int error = -ENOMEM; - int have_oldmask = 0; - cpumask_t uninitialized_var(oldmask); - - rqstp = svc_prepare_thread(serv, pool); - if (IS_ERR(rqstp)) { - error = PTR_ERR(rqstp); - goto out; - } - - if (serv->sv_nrpools > 1) - have_oldmask = svc_pool_map_set_cpumask(pool->sp_id, &oldmask); - - error = kernel_thread((int (*)(void *)) func, rqstp, 0); - - if (have_oldmask) - set_cpus_allowed(current, oldmask); - - if (error < 0) - goto out_thread; - svc_sock_update_bufs(serv); - error = 0; -out: - return error; - -out_thread: - svc_exit_thread(rqstp); - goto out; -} - /* * Choose a pool in which to create a new thread, for svc_set_num_threads */ @@ -688,7 +638,9 @@ found_pool: int svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) { - struct task_struct *victim; + struct svc_rqst *rqstp; + struct task_struct *task; + struct svc_pool *chosen_pool; int error = 0; unsigned int state = serv->sv_nrthreads-1; @@ -704,18 +656,34 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) /* create new threads */ while (nrservs > 0) { nrservs--; - __module_get(serv->sv_module); - error = __svc_create_thread(serv->sv_function, serv, - choose_pool(serv, pool, &state)); - if (error < 0) { - module_put(serv->sv_module); + chosen_pool = choose_pool(serv, pool, &state); + + rqstp = svc_prepare_thread(serv, chosen_pool); + if (IS_ERR(rqstp)) { + error = PTR_ERR(rqstp); break; } + + __module_get(serv->sv_module); + task = kthread_create(serv->sv_function, rqstp, serv->sv_name); + if (IS_ERR(task)) { + error = PTR_ERR(task); + module_put(serv->sv_module); + svc_exit_thread(rqstp); + break; + } + + rqstp->rq_task = task; + if (serv->sv_nrpools > 1) + svc_pool_map_set_cpumask(task, chosen_pool->sp_id); + + svc_sock_update_bufs(serv); + wake_up_process(task); } /* destroy old threads */ while (nrservs < 0 && - (victim = choose_victim(serv, pool, &state)) != NULL) { - send_sig(serv->sv_kill_signal, victim, 1); + (task = choose_victim(serv, pool, &state)) != NULL) { + send_sig(serv->sv_kill_signal, task, 1); nrservs++; } From a75c5d01e4235a7dd785548ac756f248b1b40107 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 10 Jun 2008 08:40:39 -0400 Subject: [PATCH 11/51] sunrpc: remove sv_kill_signal field from svc_serv struct Since we no longer make any distinction between shutdown signals with nfsd, then it becomes easier to just standardize on a particular signal to use to bring it down (SIGINT, in this case). Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfssvc.c | 3 +-- include/linux/sunrpc/svc.h | 5 ++--- net/sunrpc/svc.c | 5 ++--- 3 files changed, 5 insertions(+), 8 deletions(-) diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 9e2156813710..26c81149d49a 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -236,8 +236,7 @@ int nfsd_create_serv(void) atomic_set(&nfsd_busy, 0); nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize, - nfsd_last_thread, nfsd, SIGINT, - THIS_MODULE); + nfsd_last_thread, nfsd, THIS_MODULE); if (nfsd_serv == NULL) err = -ENOMEM; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 011d6d8100d8..dc69068d94c7 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -80,7 +80,6 @@ struct svc_serv { struct module * sv_module; /* optional module to count when * adding threads */ svc_thread_fn sv_function; /* main function for threads */ - int sv_kill_signal; /* signal to kill threads */ }; /* @@ -388,8 +387,8 @@ struct svc_rqst *svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool); void svc_exit_thread(struct svc_rqst *); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, - void (*shutdown)(struct svc_serv*), - svc_thread_fn, int sig, struct module *); + void (*shutdown)(struct svc_serv*), svc_thread_fn, + struct module *); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); void svc_destroy(struct svc_serv *); int svc_process(struct svc_rqst *); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 03a9f1a9e75c..5a32cb7c4bb4 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -434,7 +434,7 @@ EXPORT_SYMBOL(svc_create); struct svc_serv * svc_create_pooled(struct svc_program *prog, unsigned int bufsize, void (*shutdown)(struct svc_serv *serv), - svc_thread_fn func, int sig, struct module *mod) + svc_thread_fn func, struct module *mod) { struct svc_serv *serv; unsigned int npools = svc_pool_map_get(); @@ -443,7 +443,6 @@ svc_create_pooled(struct svc_program *prog, unsigned int bufsize, if (serv != NULL) { serv->sv_function = func; - serv->sv_kill_signal = sig; serv->sv_module = mod; } @@ -683,7 +682,7 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) /* destroy old threads */ while (nrservs < 0 && (task = choose_victim(serv, pool, &state)) != NULL) { - send_sig(serv->sv_kill_signal, task, 1); + send_sig(SIGINT, task, 1); nrservs++; } From abd1ec4efd82ca06127bce833ad8a4bbec8a0dcb Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 11 Jun 2008 10:03:12 -0400 Subject: [PATCH 12/51] lockd: close potential race with rapid lockd_up/lockd_down cycle If lockd_down is called very rapidly after lockd_up returns, then there is a slim chance that lockd() will never be called. kthread() will return before calling the function, so we'll end up never actually calling the cleanup functions for the thread. Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/lockd/svc.c | 33 +++++++++++++-------------------- 1 file changed, 13 insertions(+), 20 deletions(-) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 2169af4d5455..5bd9bf0fa9df 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -50,7 +50,7 @@ EXPORT_SYMBOL(nlmsvc_ops); static DEFINE_MUTEX(nlmsvc_mutex); static unsigned int nlmsvc_users; static struct task_struct *nlmsvc_task; -static struct svc_serv *nlmsvc_serv; +static struct svc_rqst *nlmsvc_rqst; int nlmsvc_grace_period; unsigned long nlmsvc_timeout; @@ -194,20 +194,11 @@ lockd(void *vrqstp) svc_process(rqstp); } - flush_signals(current); if (nlmsvc_ops) nlmsvc_invalidate_all(); nlm_shutdown_hosts(); - unlock_kernel(); - - nlmsvc_task = NULL; - nlmsvc_serv = NULL; - - /* Exit the RPC thread */ - svc_exit_thread(rqstp); - return 0; } @@ -254,16 +245,15 @@ int lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */ { struct svc_serv *serv; - struct svc_rqst *rqstp; int error = 0; mutex_lock(&nlmsvc_mutex); /* * Check whether we're already up and running. */ - if (nlmsvc_serv) { + if (nlmsvc_rqst) { if (proto) - error = make_socks(nlmsvc_serv, proto); + error = make_socks(nlmsvc_rqst->rq_server, proto); goto out; } @@ -288,9 +278,10 @@ lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */ /* * Create the kernel thread and wait for it to start. */ - rqstp = svc_prepare_thread(serv, &serv->sv_pools[0]); - if (IS_ERR(rqstp)) { - error = PTR_ERR(rqstp); + nlmsvc_rqst = svc_prepare_thread(serv, &serv->sv_pools[0]); + if (IS_ERR(nlmsvc_rqst)) { + error = PTR_ERR(nlmsvc_rqst); + nlmsvc_rqst = NULL; printk(KERN_WARNING "lockd_up: svc_rqst allocation failed, error=%d\n", error); @@ -298,16 +289,15 @@ lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */ } svc_sock_update_bufs(serv); - nlmsvc_serv = rqstp->rq_server; - nlmsvc_task = kthread_run(lockd, rqstp, serv->sv_name); + nlmsvc_task = kthread_run(lockd, nlmsvc_rqst, serv->sv_name); if (IS_ERR(nlmsvc_task)) { error = PTR_ERR(nlmsvc_task); + svc_exit_thread(nlmsvc_rqst); nlmsvc_task = NULL; - nlmsvc_serv = NULL; + nlmsvc_rqst = NULL; printk(KERN_WARNING "lockd_up: kthread_run failed, error=%d\n", error); - svc_exit_thread(rqstp); goto destroy_and_out; } @@ -346,6 +336,9 @@ lockd_down(void) BUG(); } kthread_stop(nlmsvc_task); + svc_exit_thread(nlmsvc_rqst); + nlmsvc_task = NULL; + nlmsvc_rqst = NULL; out: mutex_unlock(&nlmsvc_mutex); } From c7d106c90ec40a0e35a6960157b40f238627246e Mon Sep 17 00:00:00 2001 From: Neil Brown Date: Thu, 12 Jun 2008 13:38:42 +1000 Subject: [PATCH 13/51] nfsd: fix race in nfsd_nrthreads() We need the nfsd_mutex before accessing nfsd_serv->sv_nrthreads or we can't even guarantee nfsd_serv will still be there. Signed-off-by: Neil Brown Acked-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfssvc.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 26c81149d49a..96fdbcab8d95 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -165,10 +165,12 @@ int nfsd_vers(int vers, enum vers_op change) int nfsd_nrthreads(void) { - if (nfsd_serv == NULL) - return 0; - else - return nfsd_serv->sv_nrthreads; + int rv = 0; + mutex_lock(&nfsd_mutex); + if (nfsd_serv) + rv = nfsd_serv->sv_nrthreads; + mutex_unlock(&nfsd_mutex); + return rv; } static void nfsd_last_thread(struct svc_serv *serv) From 599eb3046a1380f31c65715f3940184c531c90cb Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 19 Jun 2008 10:11:09 +1000 Subject: [PATCH 14/51] knfsd: nfsd: Handle ERESTARTSYS from syscalls. OCFS2 can return -ERESTARTSYS from write requests (and possibly elsewhere) if there is a signal pending. If nfsd is shutdown (by sending a signal to each thread) while there is still an IO load from the client, each thread could handle one last request with a signal pending. This can result in -ERESTARTSYS which is not understood by nfserrno() and so is reflected back to the client as nfserr_io aka -EIO. This is wrong. Instead, interpret ERESTARTSYS to mean "try again later" by returning nfserr_jukebox. The client will resend and - if the server is restarted - the write will (hopefully) be successful and everyone will be happy. The symptom that I narrowed down to this was: copy a large file via NFS to an OCFS2 filesystem, and restart the nfs server during the copy. The 'cp' might get an -EIO, and the file will be corrupted - presumably holes in the middle where writes appeared to fail. Signed-off-by: Neil Brown Signed-off-by: J. Bruce Fields --- fs/nfsd/nfsproc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 6cfc96a12483..b5a20c486712 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -614,6 +614,7 @@ nfserrno (int errno) #endif { nfserr_stale, -ESTALE }, { nfserr_jukebox, -ETIMEDOUT }, + { nfserr_jukebox, -ERESTARTSYS }, { nfserr_dropit, -EAGAIN }, { nfserr_dropit, -ENOMEM }, { nfserr_badname, -ESRCH }, From 8837abcab3d16608bd2c7fac051a839d48f2f30c Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 16 Jun 2008 13:20:29 +0200 Subject: [PATCH 15/51] nfsd: rename MAY_ flags Rename nfsd_permission() specific MAY_* flags to NFSD_MAY_* to make it clear, that these are not used outside nfsd, and to avoid name and number space conflicts with the VFS. [comment from hch: rename MAY_READ, MAY_WRITE and MAY_EXEC as well] Signed-off-by: Miklos Szeredi Signed-off-by: J. Bruce Fields --- fs/nfsd/lockd.c | 2 +- fs/nfsd/nfs2acl.c | 7 ++- fs/nfsd/nfs3acl.c | 5 +- fs/nfsd/nfs3proc.c | 8 +-- fs/nfsd/nfs4proc.c | 23 ++++---- fs/nfsd/nfs4state.c | 6 +- fs/nfsd/nfsfh.c | 2 +- fs/nfsd/nfsproc.c | 8 +-- fs/nfsd/vfs.c | 115 +++++++++++++++++++------------------- include/linux/nfsd/nfsd.h | 26 ++++----- 10 files changed, 105 insertions(+), 97 deletions(-) diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c index 9e4a568a5013..6b6225ac4926 100644 --- a/fs/nfsd/lockd.c +++ b/fs/nfsd/lockd.c @@ -35,7 +35,7 @@ nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp) fh.fh_export = NULL; exp_readlock(); - nfserr = nfsd_open(rqstp, &fh, S_IFREG, MAY_LOCK, filp); + nfserr = nfsd_open(rqstp, &fh, S_IFREG, NFSD_MAY_LOCK, filp); fh_put(&fh); rqstp->rq_client = NULL; exp_readunlock(); diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 1c3b7654e966..4e3219e84116 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -40,7 +40,8 @@ static __be32 nfsacld_proc_getacl(struct svc_rqst * rqstp, dprintk("nfsd: GETACL(2acl) %s\n", SVCFH_fmt(&argp->fh)); fh = fh_copy(&resp->fh, &argp->fh); - if ((nfserr = fh_verify(rqstp, &resp->fh, 0, MAY_NOP))) + nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP); + if (nfserr) RETURN_STATUS(nfserr); if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT)) @@ -107,7 +108,7 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp, dprintk("nfsd: SETACL(2acl) %s\n", SVCFH_fmt(&argp->fh)); fh = fh_copy(&resp->fh, &argp->fh); - nfserr = fh_verify(rqstp, &resp->fh, 0, MAY_SATTR); + nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_SATTR); if (!nfserr) { nfserr = nfserrno( nfsd_set_posix_acl( @@ -134,7 +135,7 @@ static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp, dprintk("nfsd: GETATTR %s\n", SVCFH_fmt(&argp->fh)); fh_copy(&resp->fh, &argp->fh); - return fh_verify(rqstp, &resp->fh, 0, MAY_NOP); + return fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP); } /* diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index b647f2f872dc..9981dbb377a3 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -36,7 +36,8 @@ static __be32 nfsd3_proc_getacl(struct svc_rqst * rqstp, __be32 nfserr = 0; fh = fh_copy(&resp->fh, &argp->fh); - if ((nfserr = fh_verify(rqstp, &resp->fh, 0, MAY_NOP))) + nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP); + if (nfserr) RETURN_STATUS(nfserr); if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT)) @@ -101,7 +102,7 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst * rqstp, __be32 nfserr = 0; fh = fh_copy(&resp->fh, &argp->fh); - nfserr = fh_verify(rqstp, &resp->fh, 0, MAY_SATTR); + nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_SATTR); if (!nfserr) { nfserr = nfserrno( nfsd_set_posix_acl( diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index c721a1e6e9dd..4d617ea28cfc 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -63,7 +63,7 @@ nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp, SVCFH_fmt(&argp->fh)); fh_copy(&resp->fh, &argp->fh); - nfserr = fh_verify(rqstp, &resp->fh, 0, MAY_NOP); + nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP); if (nfserr) RETURN_STATUS(nfserr); @@ -242,7 +242,7 @@ nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp, attr = &argp->attrs; /* Get the directory inode */ - nfserr = fh_verify(rqstp, dirfhp, S_IFDIR, MAY_CREATE); + nfserr = fh_verify(rqstp, dirfhp, S_IFDIR, NFSD_MAY_CREATE); if (nfserr) RETURN_STATUS(nfserr); @@ -558,7 +558,7 @@ nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, resp->f_maxfilesize = ~(u32) 0; resp->f_properties = NFS3_FSF_DEFAULT; - nfserr = fh_verify(rqstp, &argp->fh, 0, MAY_NOP); + nfserr = fh_verify(rqstp, &argp->fh, 0, NFSD_MAY_NOP); /* Check special features of the file system. May request * different read/write sizes for file systems known to have @@ -597,7 +597,7 @@ nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, resp->p_case_insensitive = 0; resp->p_case_preserving = 1; - nfserr = fh_verify(rqstp, &argp->fh, 0, MAY_NOP); + nfserr = fh_verify(rqstp, &argp->fh, 0, NFSD_MAY_NOP); if (nfserr == 0) { struct super_block *sb = argp->fh.fh_dentry->d_inode->i_sb; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 313484380a9b..5c3683cfd59e 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -71,11 +71,11 @@ do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfs return nfserr_inval; if (open->op_share_access & NFS4_SHARE_ACCESS_READ) - accmode |= MAY_READ; + accmode |= NFSD_MAY_READ; if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) - accmode |= (MAY_WRITE | MAY_TRUNC); + accmode |= (NFSD_MAY_WRITE | NFSD_MAY_TRUNC); if (open->op_share_deny & NFS4_SHARE_DENY_WRITE) - accmode |= MAY_WRITE; + accmode |= NFSD_MAY_WRITE; status = fh_verify(rqstp, current_fh, S_IFREG, accmode); @@ -126,7 +126,8 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o &resfh.fh_handle.fh_base, resfh.fh_handle.fh_size); if (!created) - status = do_open_permission(rqstp, current_fh, open, MAY_NOP); + status = do_open_permission(rqstp, current_fh, open, + NFSD_MAY_NOP); out: fh_put(&resfh); @@ -157,7 +158,8 @@ do_open_fhandle(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_ open->op_truncate = (open->op_iattr.ia_valid & ATTR_SIZE) && (open->op_iattr.ia_size == 0); - status = do_open_permission(rqstp, current_fh, open, MAY_OWNER_OVERRIDE); + status = do_open_permission(rqstp, current_fh, open, + NFSD_MAY_OWNER_OVERRIDE); return status; } @@ -186,7 +188,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, cstate->current_fh.fh_handle.fh_size = rp->rp_openfh_len; memcpy(&cstate->current_fh.fh_handle.fh_base, rp->rp_openfh, rp->rp_openfh_len); - status = fh_verify(rqstp, &cstate->current_fh, 0, MAY_NOP); + status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP); if (status) dprintk("nfsd4_open: replay failed" " restoring previous filehandle\n"); @@ -285,7 +287,7 @@ nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen; memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval, putfh->pf_fhlen); - return fh_verify(rqstp, &cstate->current_fh, 0, MAY_NOP); + return fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP); } static __be32 @@ -363,7 +365,8 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fh_init(&resfh, NFS4_FHSIZE); - status = fh_verify(rqstp, &cstate->current_fh, S_IFDIR, MAY_CREATE); + status = fh_verify(rqstp, &cstate->current_fh, S_IFDIR, + NFSD_MAY_CREATE); if (status == nfserr_symlink) status = nfserr_notdir; if (status) @@ -445,7 +448,7 @@ nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, { __be32 status; - status = fh_verify(rqstp, &cstate->current_fh, 0, MAY_NOP); + status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP); if (status) return status; @@ -730,7 +733,7 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, int count; __be32 status; - status = fh_verify(rqstp, &cstate->current_fh, 0, MAY_NOP); + status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP); if (status) return status; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index bf11d6879ab4..eca8aaa450f1 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1722,9 +1722,9 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf /* Stateid was not found, this is a new OPEN */ int flags = 0; if (open->op_share_access & NFS4_SHARE_ACCESS_READ) - flags |= MAY_READ; + flags |= NFSD_MAY_READ; if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) - flags |= MAY_WRITE; + flags |= NFSD_MAY_WRITE; status = nfs4_new_open(rqstp, &stp, dp, current_fh, flags); if (status) goto out; @@ -2610,7 +2610,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfserr_inval; if ((status = fh_verify(rqstp, &cstate->current_fh, - S_IFREG, MAY_LOCK))) { + S_IFREG, NFSD_MAY_LOCK))) { dprintk("NFSD: nfsd4_lock: permission denied!\n"); return status; } diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 100ae5641162..c7b0fdaeac96 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -279,7 +279,7 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access) if (error) goto out; - if (!(access & MAY_LOCK)) { + if (!(access & NFSD_MAY_LOCK)) { /* * pseudoflavor restrictions are not enforced on NLM, * which clients virtually always use auth_sys for, diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index b5a20c486712..0766f95d236a 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -65,7 +65,7 @@ nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp, dprintk("nfsd: GETATTR %s\n", SVCFH_fmt(&argp->fh)); fh_copy(&resp->fh, &argp->fh); - nfserr = fh_verify(rqstp, &resp->fh, 0, MAY_NOP); + nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP); return nfsd_return_attrs(nfserr, resp); } @@ -215,11 +215,11 @@ nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp, SVCFH_fmt(dirfhp), argp->len, argp->name); /* First verify the parent file handle */ - nfserr = fh_verify(rqstp, dirfhp, S_IFDIR, MAY_EXEC); + nfserr = fh_verify(rqstp, dirfhp, S_IFDIR, NFSD_MAY_EXEC); if (nfserr) goto done; /* must fh_put dirfhp even on error */ - /* Check for MAY_WRITE in nfsd_create if necessary */ + /* Check for NFSD_MAY_WRITE in nfsd_create if necessary */ nfserr = nfserr_acces; if (!argp->len) @@ -281,7 +281,7 @@ nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp, nfserr = nfsd_permission(rqstp, newfhp->fh_export, newfhp->fh_dentry, - MAY_WRITE|MAY_LOCAL_ACCESS); + NFSD_MAY_WRITE|NFSD_MAY_LOCAL_ACCESS); if (nfserr && nfserr != nfserr_rofs) goto out_unlock; } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index a3a291f771f4..5e05ddda4560 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -144,7 +144,7 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, dprintk("nfsd: nfsd_lookup(fh %s, %.*s)\n", SVCFH_fmt(fhp), len,name); /* Obtain dentry and export. */ - err = fh_verify(rqstp, fhp, S_IFDIR, MAY_EXEC); + err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC); if (err) return err; @@ -262,14 +262,14 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, { struct dentry *dentry; struct inode *inode; - int accmode = MAY_SATTR; + int accmode = NFSD_MAY_SATTR; int ftype = 0; __be32 err; int host_err; int size_change = 0; if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE)) - accmode |= MAY_WRITE|MAY_OWNER_OVERRIDE; + accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE; if (iap->ia_valid & ATTR_SIZE) ftype = S_IFREG; @@ -331,7 +331,8 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, */ if (iap->ia_valid & ATTR_SIZE) { if (iap->ia_size < inode->i_size) { - err = nfsd_permission(rqstp, fhp->fh_export, dentry, MAY_TRUNC|MAY_OWNER_OVERRIDE); + err = nfsd_permission(rqstp, fhp->fh_export, dentry, + NFSD_MAY_TRUNC|NFSD_MAY_OWNER_OVERRIDE); if (err) goto out; } @@ -462,7 +463,7 @@ nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int flags = 0; /* Get inode */ - error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, MAY_SATTR); + error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, NFSD_MAY_SATTR); if (error) return error; @@ -563,20 +564,20 @@ struct accessmap { int how; }; static struct accessmap nfs3_regaccess[] = { - { NFS3_ACCESS_READ, MAY_READ }, - { NFS3_ACCESS_EXECUTE, MAY_EXEC }, - { NFS3_ACCESS_MODIFY, MAY_WRITE|MAY_TRUNC }, - { NFS3_ACCESS_EXTEND, MAY_WRITE }, + { NFS3_ACCESS_READ, NFSD_MAY_READ }, + { NFS3_ACCESS_EXECUTE, NFSD_MAY_EXEC }, + { NFS3_ACCESS_MODIFY, NFSD_MAY_WRITE|NFSD_MAY_TRUNC }, + { NFS3_ACCESS_EXTEND, NFSD_MAY_WRITE }, { 0, 0 } }; static struct accessmap nfs3_diraccess[] = { - { NFS3_ACCESS_READ, MAY_READ }, - { NFS3_ACCESS_LOOKUP, MAY_EXEC }, - { NFS3_ACCESS_MODIFY, MAY_EXEC|MAY_WRITE|MAY_TRUNC }, - { NFS3_ACCESS_EXTEND, MAY_EXEC|MAY_WRITE }, - { NFS3_ACCESS_DELETE, MAY_REMOVE }, + { NFS3_ACCESS_READ, NFSD_MAY_READ }, + { NFS3_ACCESS_LOOKUP, NFSD_MAY_EXEC }, + { NFS3_ACCESS_MODIFY, NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC}, + { NFS3_ACCESS_EXTEND, NFSD_MAY_EXEC|NFSD_MAY_WRITE }, + { NFS3_ACCESS_DELETE, NFSD_MAY_REMOVE }, { 0, 0 } }; @@ -589,10 +590,10 @@ static struct accessmap nfs3_anyaccess[] = { * mainly at mode bits, and we make sure to ignore read-only * filesystem checks */ - { NFS3_ACCESS_READ, MAY_READ }, - { NFS3_ACCESS_EXECUTE, MAY_EXEC }, - { NFS3_ACCESS_MODIFY, MAY_WRITE|MAY_LOCAL_ACCESS }, - { NFS3_ACCESS_EXTEND, MAY_WRITE|MAY_LOCAL_ACCESS }, + { NFS3_ACCESS_READ, NFSD_MAY_READ }, + { NFS3_ACCESS_EXECUTE, NFSD_MAY_EXEC }, + { NFS3_ACCESS_MODIFY, NFSD_MAY_WRITE|NFSD_MAY_LOCAL_ACCESS }, + { NFS3_ACCESS_EXTEND, NFSD_MAY_WRITE|NFSD_MAY_LOCAL_ACCESS }, { 0, 0 } }; @@ -606,7 +607,7 @@ nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *suppor u32 query, result = 0, sresult = 0; __be32 error; - error = fh_verify(rqstp, fhp, 0, MAY_NOP); + error = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP); if (error) goto out; @@ -678,7 +679,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, * and (hopefully) checked permission - so allow OWNER_OVERRIDE * in case a chmod has now revoked permission. */ - err = fh_verify(rqstp, fhp, type, access | MAY_OWNER_OVERRIDE); + err = fh_verify(rqstp, fhp, type, access | NFSD_MAY_OWNER_OVERRIDE); if (err) goto out; @@ -689,7 +690,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, * or any access when mandatory locking enabled */ err = nfserr_perm; - if (IS_APPEND(inode) && (access & MAY_WRITE)) + if (IS_APPEND(inode) && (access & NFSD_MAY_WRITE)) goto out; /* * We must ignore files (but only files) which might have mandatory @@ -706,14 +707,14 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, * Check to see if there are any leases on this file. * This may block while leases are broken. */ - host_err = break_lease(inode, O_NONBLOCK | ((access & MAY_WRITE) ? FMODE_WRITE : 0)); + host_err = break_lease(inode, O_NONBLOCK | ((access & NFSD_MAY_WRITE) ? FMODE_WRITE : 0)); if (host_err == -EWOULDBLOCK) host_err = -ETIMEDOUT; if (host_err) /* NOMEM or WOULDBLOCK */ goto out_nfserr; - if (access & MAY_WRITE) { - if (access & MAY_READ) + if (access & NFSD_MAY_WRITE) { + if (access & NFSD_MAY_READ) flags = O_RDWR|O_LARGEFILE; else flags = O_WRONLY|O_LARGEFILE; @@ -1069,12 +1070,12 @@ nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, if (file) { err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, - MAY_READ|MAY_OWNER_OVERRIDE); + NFSD_MAY_READ|NFSD_MAY_OWNER_OVERRIDE); if (err) goto out; err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count); } else { - err = nfsd_open(rqstp, fhp, S_IFREG, MAY_READ, &file); + err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file); if (err) goto out; err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count); @@ -1098,13 +1099,13 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, if (file) { err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, - MAY_WRITE|MAY_OWNER_OVERRIDE); + NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE); if (err) goto out; err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen, cnt, stablep); } else { - err = nfsd_open(rqstp, fhp, S_IFREG, MAY_WRITE, &file); + err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_WRITE, &file); if (err) goto out; @@ -1136,7 +1137,8 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, if ((u64)count > ~(u64)offset) return nfserr_inval; - if ((err = nfsd_open(rqstp, fhp, S_IFREG, MAY_WRITE, &file)) != 0) + err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_WRITE, &file); + if (err) return err; if (EX_ISSYNC(fhp->fh_export)) { if (file->f_op && file->f_op->fsync) { @@ -1197,7 +1199,7 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, if (isdotent(fname, flen)) goto out; - err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE); + err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE); if (err) goto out; @@ -1334,7 +1336,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out; if (!(iap->ia_valid & ATTR_MODE)) iap->ia_mode = 0; - err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE); + err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE); if (err) goto out; @@ -1471,7 +1473,7 @@ nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp) __be32 err; int host_err; - err = fh_verify(rqstp, fhp, S_IFLNK, MAY_NOP); + err = fh_verify(rqstp, fhp, S_IFLNK, NFSD_MAY_NOP); if (err) goto out; @@ -1526,7 +1528,7 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, if (isdotent(fname, flen)) goto out; - err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE); + err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE); if (err) goto out; fh_lock(fhp); @@ -1591,10 +1593,10 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, __be32 err; int host_err; - err = fh_verify(rqstp, ffhp, S_IFDIR, MAY_CREATE); + err = fh_verify(rqstp, ffhp, S_IFDIR, NFSD_MAY_CREATE); if (err) goto out; - err = fh_verify(rqstp, tfhp, -S_IFDIR, MAY_NOP); + err = fh_verify(rqstp, tfhp, -S_IFDIR, NFSD_MAY_NOP); if (err) goto out; @@ -1661,10 +1663,10 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, __be32 err; int host_err; - err = fh_verify(rqstp, ffhp, S_IFDIR, MAY_REMOVE); + err = fh_verify(rqstp, ffhp, S_IFDIR, NFSD_MAY_REMOVE); if (err) goto out; - err = fh_verify(rqstp, tfhp, S_IFDIR, MAY_CREATE); + err = fh_verify(rqstp, tfhp, S_IFDIR, NFSD_MAY_CREATE); if (err) goto out; @@ -1768,7 +1770,7 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, err = nfserr_acces; if (!flen || isdotent(fname, flen)) goto out; - err = fh_verify(rqstp, fhp, S_IFDIR, MAY_REMOVE); + err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_REMOVE); if (err) goto out; @@ -1834,7 +1836,7 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, struct file *file; loff_t offset = *offsetp; - err = nfsd_open(rqstp, fhp, S_IFDIR, MAY_READ, &file); + err = nfsd_open(rqstp, fhp, S_IFDIR, NFSD_MAY_READ, &file); if (err) goto out; @@ -1875,7 +1877,7 @@ out: __be32 nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct kstatfs *stat) { - __be32 err = fh_verify(rqstp, fhp, 0, MAY_NOP); + __be32 err = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP); if (!err && vfs_statfs(fhp->fh_dentry,stat)) err = nfserr_io; return err; @@ -1896,18 +1898,18 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, struct inode *inode = dentry->d_inode; int err; - if (acc == MAY_NOP) + if (acc == NFSD_MAY_NOP) return 0; #if 0 dprintk("nfsd: permission 0x%x%s%s%s%s%s%s%s mode 0%o%s%s%s\n", acc, - (acc & MAY_READ)? " read" : "", - (acc & MAY_WRITE)? " write" : "", - (acc & MAY_EXEC)? " exec" : "", - (acc & MAY_SATTR)? " sattr" : "", - (acc & MAY_TRUNC)? " trunc" : "", - (acc & MAY_LOCK)? " lock" : "", - (acc & MAY_OWNER_OVERRIDE)? " owneroverride" : "", + (acc & NFSD_MAY_READ)? " read" : "", + (acc & NFSD_MAY_WRITE)? " write" : "", + (acc & NFSD_MAY_EXEC)? " exec" : "", + (acc & NFSD_MAY_SATTR)? " sattr" : "", + (acc & NFSD_MAY_TRUNC)? " trunc" : "", + (acc & NFSD_MAY_LOCK)? " lock" : "", + (acc & NFSD_MAY_OWNER_OVERRIDE)? " owneroverride" : "", inode->i_mode, IS_IMMUTABLE(inode)? " immut" : "", IS_APPEND(inode)? " append" : "", @@ -1920,18 +1922,18 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, * system. But if it is IRIX doing check on write-access for a * device special file, we ignore rofs. */ - if (!(acc & MAY_LOCAL_ACCESS)) - if (acc & (MAY_WRITE | MAY_SATTR | MAY_TRUNC)) { + if (!(acc & NFSD_MAY_LOCAL_ACCESS)) + if (acc & (NFSD_MAY_WRITE | NFSD_MAY_SATTR | NFSD_MAY_TRUNC)) { if (exp_rdonly(rqstp, exp) || __mnt_is_readonly(exp->ex_path.mnt)) return nfserr_rofs; - if (/* (acc & MAY_WRITE) && */ IS_IMMUTABLE(inode)) + if (/* (acc & NFSD_MAY_WRITE) && */ IS_IMMUTABLE(inode)) return nfserr_perm; } - if ((acc & MAY_TRUNC) && IS_APPEND(inode)) + if ((acc & NFSD_MAY_TRUNC) && IS_APPEND(inode)) return nfserr_perm; - if (acc & MAY_LOCK) { + if (acc & NFSD_MAY_LOCK) { /* If we cannot rely on authentication in NLM requests, * just allow locks, otherwise require read permission, or * ownership @@ -1939,7 +1941,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, if (exp->ex_flags & NFSEXP_NOAUTHNLM) return 0; else - acc = MAY_READ | MAY_OWNER_OVERRIDE; + acc = NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE; } /* * The file owner always gets access permission for accesses that @@ -1955,15 +1957,16 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, * We must trust the client to do permission checking - using "ACCESS" * with NFSv3. */ - if ((acc & MAY_OWNER_OVERRIDE) && + if ((acc & NFSD_MAY_OWNER_OVERRIDE) && inode->i_uid == current->fsuid) return 0; + /* This assumes NFSD_MAY_{READ,WRITE,EXEC} == MAY_{READ,WRITE,EXEC} */ err = permission(inode, acc & (MAY_READ|MAY_WRITE|MAY_EXEC), NULL); /* Allow read access to binaries even when mode 111 */ if (err == -EACCES && S_ISREG(inode->i_mode) && - acc == (MAY_READ | MAY_OWNER_OVERRIDE)) + acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE)) err = permission(inode, MAY_EXEC, NULL); return err? nfserrno(err) : 0; diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 88d85b964429..a2861d95ecc3 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -28,20 +28,20 @@ #define NFSD_SUPPORTED_MINOR_VERSION 0 /* - * Special flags for nfsd_permission. These must be different from MAY_READ, - * MAY_WRITE, and MAY_EXEC. + * Flags for nfsd_permission */ -#define MAY_NOP 0 -#define MAY_SATTR 8 -#define MAY_TRUNC 16 -#define MAY_LOCK 32 -#define MAY_OWNER_OVERRIDE 64 -#define MAY_LOCAL_ACCESS 128 /* IRIX doing local access check on device special file*/ -#if (MAY_SATTR | MAY_TRUNC | MAY_LOCK | MAY_OWNER_OVERRIDE | MAY_LOCAL_ACCESS) & (MAY_READ | MAY_WRITE | MAY_EXEC) -# error "please use a different value for MAY_SATTR or MAY_TRUNC or MAY_LOCK or MAY_LOCAL_ACCESS or MAY_OWNER_OVERRIDE." -#endif -#define MAY_CREATE (MAY_EXEC|MAY_WRITE) -#define MAY_REMOVE (MAY_EXEC|MAY_WRITE|MAY_TRUNC) +#define NFSD_MAY_NOP 0 +#define NFSD_MAY_EXEC 1 /* == MAY_EXEC */ +#define NFSD_MAY_WRITE 2 /* == MAY_WRITE */ +#define NFSD_MAY_READ 4 /* == MAY_READ */ +#define NFSD_MAY_SATTR 8 +#define NFSD_MAY_TRUNC 16 +#define NFSD_MAY_LOCK 32 +#define NFSD_MAY_OWNER_OVERRIDE 64 +#define NFSD_MAY_LOCAL_ACCESS 128 /* IRIX doing local access check on device special file*/ + +#define NFSD_MAY_CREATE (NFSD_MAY_EXEC|NFSD_MAY_WRITE) +#define NFSD_MAY_REMOVE (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC) /* * Callback function for readdir From d00953a53e9a2edbe005c1e596f1e96a8a293401 Mon Sep 17 00:00:00 2001 From: Kevin Coffman Date: Wed, 30 Apr 2008 12:45:53 -0400 Subject: [PATCH 16/51] gss_krb5: create a define for token header size and clean up ptr location cleanup: Document token header size with a #define instead of open-coding it. Don't needlessly increment "ptr" past the beginning of the header which makes the values passed to functions more understandable and eliminates the need for extra "krb5_hdr" pointer. Clean up some intersecting white-space issues flagged by checkpatch.pl. This leaves the checksum length hard-coded at 8 for DES. A later patch cleans that up. Signed-off-by: Kevin Coffman Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/gss_krb5.h | 3 ++ net/sunrpc/auth_gss/gss_krb5_seal.c | 26 +++++++------- net/sunrpc/auth_gss/gss_krb5_unseal.c | 16 ++++----- net/sunrpc/auth_gss/gss_krb5_wrap.c | 50 +++++++++++++-------------- 4 files changed, 49 insertions(+), 46 deletions(-) diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index a10f1fb0bf7c..e7bbdba474d5 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -51,6 +51,9 @@ struct krb5_ctx { extern spinlock_t krb5_seq_lock; +/* The length of the Kerberos GSS token header */ +#define GSS_KRB5_TOK_HDR_LEN (16) + #define KG_TOK_MIC_MSG 0x0101 #define KG_TOK_WRAP_MSG 0x0201 diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c index 5f1d36dfbcf7..b8f42ef7178e 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seal.c +++ b/net/sunrpc/auth_gss/gss_krb5_seal.c @@ -78,7 +78,7 @@ gss_get_mic_kerberos(struct gss_ctx *gss_ctx, struct xdr_buf *text, struct krb5_ctx *ctx = gss_ctx->internal_ctx_id; char cksumdata[16]; struct xdr_netobj md5cksum = {.len = 0, .data = cksumdata}; - unsigned char *ptr, *krb5_hdr, *msg_start; + unsigned char *ptr, *msg_start; s32 now; u32 seq_send; @@ -87,36 +87,36 @@ gss_get_mic_kerberos(struct gss_ctx *gss_ctx, struct xdr_buf *text, now = get_seconds(); - token->len = g_token_size(&ctx->mech_used, 24); + token->len = g_token_size(&ctx->mech_used, GSS_KRB5_TOK_HDR_LEN + 8); ptr = token->data; - g_make_token_header(&ctx->mech_used, 24, &ptr); + g_make_token_header(&ctx->mech_used, GSS_KRB5_TOK_HDR_LEN + 8, &ptr); - *ptr++ = (unsigned char) ((KG_TOK_MIC_MSG>>8)&0xff); - *ptr++ = (unsigned char) (KG_TOK_MIC_MSG&0xff); + /* ptr now at header described in rfc 1964, section 1.2.1: */ + ptr[0] = (unsigned char) ((KG_TOK_MIC_MSG >> 8) & 0xff); + ptr[1] = (unsigned char) (KG_TOK_MIC_MSG & 0xff); - /* ptr now at byte 2 of header described in rfc 1964, section 1.2.1: */ - krb5_hdr = ptr - 2; - msg_start = krb5_hdr + 24; + msg_start = ptr + GSS_KRB5_TOK_HDR_LEN + 8; - *(__be16 *)(krb5_hdr + 2) = htons(SGN_ALG_DES_MAC_MD5); - memset(krb5_hdr + 4, 0xff, 4); + *(__be16 *)(ptr + 2) = htons(SGN_ALG_DES_MAC_MD5); + memset(ptr + 4, 0xff, 4); - if (make_checksum("md5", krb5_hdr, 8, text, 0, &md5cksum)) + if (make_checksum("md5", ptr, 8, text, 0, &md5cksum)) return GSS_S_FAILURE; if (krb5_encrypt(ctx->seq, NULL, md5cksum.data, md5cksum.data, md5cksum.len)) return GSS_S_FAILURE; - memcpy(krb5_hdr + 16, md5cksum.data + md5cksum.len - 8, 8); + memcpy(ptr + GSS_KRB5_TOK_HDR_LEN, md5cksum.data + md5cksum.len - 8, 8); spin_lock(&krb5_seq_lock); seq_send = ctx->seq_send++; spin_unlock(&krb5_seq_lock); if (krb5_make_seq_num(ctx->seq, ctx->initiate ? 0 : 0xff, - seq_send, krb5_hdr + 16, krb5_hdr + 8)) + seq_send, ptr + GSS_KRB5_TOK_HDR_LEN, + ptr + 8)) return GSS_S_FAILURE; return (ctx->endtime < now) ? GSS_S_CONTEXT_EXPIRED : GSS_S_COMPLETE; diff --git a/net/sunrpc/auth_gss/gss_krb5_unseal.c b/net/sunrpc/auth_gss/gss_krb5_unseal.c index d91a5d004803..066ec73c84d6 100644 --- a/net/sunrpc/auth_gss/gss_krb5_unseal.c +++ b/net/sunrpc/auth_gss/gss_krb5_unseal.c @@ -92,30 +92,30 @@ gss_verify_mic_kerberos(struct gss_ctx *gss_ctx, read_token->len)) return GSS_S_DEFECTIVE_TOKEN; - if ((*ptr++ != ((KG_TOK_MIC_MSG>>8)&0xff)) || - (*ptr++ != ( KG_TOK_MIC_MSG &0xff)) ) + if ((ptr[0] != ((KG_TOK_MIC_MSG >> 8) & 0xff)) || + (ptr[1] != (KG_TOK_MIC_MSG & 0xff))) return GSS_S_DEFECTIVE_TOKEN; /* XXX sanity-check bodysize?? */ - signalg = ptr[0] + (ptr[1] << 8); + signalg = ptr[2] + (ptr[3] << 8); if (signalg != SGN_ALG_DES_MAC_MD5) return GSS_S_DEFECTIVE_TOKEN; - sealalg = ptr[2] + (ptr[3] << 8); + sealalg = ptr[4] + (ptr[5] << 8); if (sealalg != SEAL_ALG_NONE) return GSS_S_DEFECTIVE_TOKEN; - if ((ptr[4] != 0xff) || (ptr[5] != 0xff)) + if ((ptr[6] != 0xff) || (ptr[7] != 0xff)) return GSS_S_DEFECTIVE_TOKEN; - if (make_checksum("md5", ptr - 2, 8, message_buffer, 0, &md5cksum)) + if (make_checksum("md5", ptr, 8, message_buffer, 0, &md5cksum)) return GSS_S_FAILURE; if (krb5_encrypt(ctx->seq, NULL, md5cksum.data, md5cksum.data, 16)) return GSS_S_FAILURE; - if (memcmp(md5cksum.data + 8, ptr + 14, 8)) + if (memcmp(md5cksum.data + 8, ptr + GSS_KRB5_TOK_HDR_LEN, 8)) return GSS_S_BAD_SIG; /* it got through unscathed. Make sure the context is unexpired */ @@ -127,7 +127,7 @@ gss_verify_mic_kerberos(struct gss_ctx *gss_ctx, /* do sequencing checks */ - if (krb5_get_seq_num(ctx->seq, ptr + 14, ptr + 6, &direction, &seqnum)) + if (krb5_get_seq_num(ctx->seq, ptr + GSS_KRB5_TOK_HDR_LEN, ptr + 8, &direction, &seqnum)) return GSS_S_FAILURE; if ((ctx->initiate && direction != 0xff) || diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index b00b1b426301..283cb25c6237 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -122,7 +122,7 @@ gss_wrap_kerberos(struct gss_ctx *ctx, int offset, char cksumdata[16]; struct xdr_netobj md5cksum = {.len = 0, .data = cksumdata}; int blocksize = 0, plainlen; - unsigned char *ptr, *krb5_hdr, *msg_start; + unsigned char *ptr, *msg_start; s32 now; int headlen; struct page **tmp_pages; @@ -149,26 +149,26 @@ gss_wrap_kerberos(struct gss_ctx *ctx, int offset, buf->len += headlen; BUG_ON((buf->len - offset - headlen) % blocksize); - g_make_token_header(&kctx->mech_used, 24 + plainlen, &ptr); + g_make_token_header(&kctx->mech_used, + GSS_KRB5_TOK_HDR_LEN + 8 + plainlen, &ptr); - *ptr++ = (unsigned char) ((KG_TOK_WRAP_MSG>>8)&0xff); - *ptr++ = (unsigned char) (KG_TOK_WRAP_MSG&0xff); + /* ptr now at header described in rfc 1964, section 1.2.1: */ + ptr[0] = (unsigned char) ((KG_TOK_WRAP_MSG >> 8) & 0xff); + ptr[1] = (unsigned char) (KG_TOK_WRAP_MSG & 0xff); - /* ptr now at byte 2 of header described in rfc 1964, section 1.2.1: */ - krb5_hdr = ptr - 2; - msg_start = krb5_hdr + 24; + msg_start = ptr + 24; - *(__be16 *)(krb5_hdr + 2) = htons(SGN_ALG_DES_MAC_MD5); - memset(krb5_hdr + 4, 0xff, 4); - *(__be16 *)(krb5_hdr + 4) = htons(SEAL_ALG_DES); + *(__be16 *)(ptr + 2) = htons(SGN_ALG_DES_MAC_MD5); + memset(ptr + 4, 0xff, 4); + *(__be16 *)(ptr + 4) = htons(SEAL_ALG_DES); make_confounder(msg_start, blocksize); /* XXXJBF: UGH!: */ tmp_pages = buf->pages; buf->pages = pages; - if (make_checksum("md5", krb5_hdr, 8, buf, + if (make_checksum("md5", ptr, 8, buf, offset + headlen - blocksize, &md5cksum)) return GSS_S_FAILURE; buf->pages = tmp_pages; @@ -176,7 +176,7 @@ gss_wrap_kerberos(struct gss_ctx *ctx, int offset, if (krb5_encrypt(kctx->seq, NULL, md5cksum.data, md5cksum.data, md5cksum.len)) return GSS_S_FAILURE; - memcpy(krb5_hdr + 16, md5cksum.data + md5cksum.len - 8, 8); + memcpy(ptr + GSS_KRB5_TOK_HDR_LEN, md5cksum.data + md5cksum.len - 8, 8); spin_lock(&krb5_seq_lock); seq_send = kctx->seq_send++; @@ -185,7 +185,7 @@ gss_wrap_kerberos(struct gss_ctx *ctx, int offset, /* XXX would probably be more efficient to compute checksum * and encrypt at the same time: */ if ((krb5_make_seq_num(kctx->seq, kctx->initiate ? 0 : 0xff, - seq_send, krb5_hdr + 16, krb5_hdr + 8))) + seq_send, ptr + GSS_KRB5_TOK_HDR_LEN, ptr + 8))) return GSS_S_FAILURE; if (gss_encrypt_xdr_buf(kctx->enc, buf, offset + headlen - blocksize, @@ -219,38 +219,38 @@ gss_unwrap_kerberos(struct gss_ctx *ctx, int offset, struct xdr_buf *buf) buf->len - offset)) return GSS_S_DEFECTIVE_TOKEN; - if ((*ptr++ != ((KG_TOK_WRAP_MSG>>8)&0xff)) || - (*ptr++ != (KG_TOK_WRAP_MSG &0xff)) ) + if ((ptr[0] != ((KG_TOK_WRAP_MSG >> 8) & 0xff)) || + (ptr[1] != (KG_TOK_WRAP_MSG & 0xff))) return GSS_S_DEFECTIVE_TOKEN; /* XXX sanity-check bodysize?? */ /* get the sign and seal algorithms */ - signalg = ptr[0] + (ptr[1] << 8); + signalg = ptr[2] + (ptr[3] << 8); if (signalg != SGN_ALG_DES_MAC_MD5) return GSS_S_DEFECTIVE_TOKEN; - sealalg = ptr[2] + (ptr[3] << 8); + sealalg = ptr[4] + (ptr[5] << 8); if (sealalg != SEAL_ALG_DES) return GSS_S_DEFECTIVE_TOKEN; - if ((ptr[4] != 0xff) || (ptr[5] != 0xff)) + if ((ptr[6] != 0xff) || (ptr[7] != 0xff)) return GSS_S_DEFECTIVE_TOKEN; if (gss_decrypt_xdr_buf(kctx->enc, buf, - ptr + 22 - (unsigned char *)buf->head[0].iov_base)) + ptr + GSS_KRB5_TOK_HDR_LEN + 8 - (unsigned char *)buf->head[0].iov_base)) return GSS_S_DEFECTIVE_TOKEN; - if (make_checksum("md5", ptr - 2, 8, buf, - ptr + 22 - (unsigned char *)buf->head[0].iov_base, &md5cksum)) + if (make_checksum("md5", ptr, 8, buf, + ptr + GSS_KRB5_TOK_HDR_LEN + 8 - (unsigned char *)buf->head[0].iov_base, &md5cksum)) return GSS_S_FAILURE; if (krb5_encrypt(kctx->seq, NULL, md5cksum.data, md5cksum.data, md5cksum.len)) return GSS_S_FAILURE; - if (memcmp(md5cksum.data + 8, ptr + 14, 8)) + if (memcmp(md5cksum.data + 8, ptr + GSS_KRB5_TOK_HDR_LEN, 8)) return GSS_S_BAD_SIG; /* it got through unscathed. Make sure the context is unexpired */ @@ -262,8 +262,8 @@ gss_unwrap_kerberos(struct gss_ctx *ctx, int offset, struct xdr_buf *buf) /* do sequencing checks */ - if (krb5_get_seq_num(kctx->seq, ptr + 14, ptr + 6, &direction, - &seqnum)) + if (krb5_get_seq_num(kctx->seq, ptr + GSS_KRB5_TOK_HDR_LEN, ptr + 8, + &direction, &seqnum)) return GSS_S_BAD_SIG; if ((kctx->initiate && direction != 0xff) || @@ -274,7 +274,7 @@ gss_unwrap_kerberos(struct gss_ctx *ctx, int offset, struct xdr_buf *buf) * better to copy and encrypt at the same time. */ blocksize = crypto_blkcipher_blocksize(kctx->enc); - data_start = ptr + 22 + blocksize; + data_start = ptr + GSS_KRB5_TOK_HDR_LEN + 8 + blocksize; orig_start = buf->head[0].iov_base + offset; data_len = (buf->head[0].iov_base + buf->head[0].iov_len) - data_start; memmove(orig_start, data_start, data_len); From db8add57898751b9c0ff93ead25f20d21da5ddd0 Mon Sep 17 00:00:00 2001 From: Kevin Coffman Date: Wed, 30 Apr 2008 12:45:58 -0400 Subject: [PATCH 17/51] gss_krb5: move gss_krb5_crypto into the krb5 module The gss_krb5_crypto.o object belongs in the rpcsec_gss_krb5 module. Also, there is no need to export symbols from gss_krb5_crypto.c Signed-off-by: Kevin Coffman Signed-off-by: J. Bruce Fields --- net/sunrpc/auth_gss/Makefile | 4 ++-- net/sunrpc/auth_gss/gss_krb5_crypto.c | 10 ---------- 2 files changed, 2 insertions(+), 12 deletions(-) diff --git a/net/sunrpc/auth_gss/Makefile b/net/sunrpc/auth_gss/Makefile index f3431a7e33da..4de8bcf26fa7 100644 --- a/net/sunrpc/auth_gss/Makefile +++ b/net/sunrpc/auth_gss/Makefile @@ -5,12 +5,12 @@ obj-$(CONFIG_SUNRPC_GSS) += auth_rpcgss.o auth_rpcgss-objs := auth_gss.o gss_generic_token.o \ - gss_mech_switch.o svcauth_gss.o gss_krb5_crypto.o + gss_mech_switch.o svcauth_gss.o obj-$(CONFIG_RPCSEC_GSS_KRB5) += rpcsec_gss_krb5.o rpcsec_gss_krb5-objs := gss_krb5_mech.o gss_krb5_seal.o gss_krb5_unseal.o \ - gss_krb5_seqnum.o gss_krb5_wrap.o + gss_krb5_seqnum.o gss_krb5_wrap.o gss_krb5_crypto.o obj-$(CONFIG_RPCSEC_GSS_SPKM3) += rpcsec_gss_spkm3.o diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 1d52308ca324..c93fca204558 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -83,8 +83,6 @@ out: return ret; } -EXPORT_SYMBOL(krb5_encrypt); - u32 krb5_decrypt( struct crypto_blkcipher *tfm, @@ -118,8 +116,6 @@ out: return ret; } -EXPORT_SYMBOL(krb5_decrypt); - static int checksummer(struct scatterlist *sg, void *data) { @@ -161,8 +157,6 @@ out: return err ? GSS_S_FAILURE : 0; } -EXPORT_SYMBOL(make_checksum); - struct encryptor_desc { u8 iv[8]; /* XXX hard-coded blocksize */ struct blkcipher_desc desc; @@ -262,8 +256,6 @@ gss_encrypt_xdr_buf(struct crypto_blkcipher *tfm, struct xdr_buf *buf, return ret; } -EXPORT_SYMBOL(gss_encrypt_xdr_buf); - struct decryptor_desc { u8 iv[8]; /* XXX hard-coded blocksize */ struct blkcipher_desc desc; @@ -334,5 +326,3 @@ gss_decrypt_xdr_buf(struct crypto_blkcipher *tfm, struct xdr_buf *buf, return xdr_process_buf(buf, offset, buf->len - offset, decryptor, &desc); } - -EXPORT_SYMBOL(gss_decrypt_xdr_buf); From 863a24882ed0a57ff25daaf39885f3a47b706e4b Mon Sep 17 00:00:00 2001 From: Kevin Coffman Date: Wed, 30 Apr 2008 12:46:08 -0400 Subject: [PATCH 18/51] gss_krb5: Use random value to initialize confounder Initialize the value used for the confounder to a random value rather than starting from zero. Allow for confounders of length 8 or 16 (which will be needed for AES). Signed-off-by: Kevin Coffman Signed-off-by: J. Bruce Fields --- net/sunrpc/auth_gss/gss_krb5_wrap.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 283cb25c6237..ae8e69b59c4c 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -87,8 +87,8 @@ out: return 0; } -static inline void -make_confounder(char *p, int blocksize) +static void +make_confounder(char *p, u32 conflen) { static u64 i = 0; u64 *q = (u64 *)p; @@ -102,8 +102,22 @@ make_confounder(char *p, int blocksize) * uniqueness would mean worrying about atomicity and rollover, and I * don't care enough. */ - BUG_ON(blocksize != 8); - *q = i++; + /* initialize to random value */ + if (i == 0) { + i = random32(); + i = (i << 32) | random32(); + } + + switch (conflen) { + case 16: + *q++ = i++; + /* fall through */ + case 8: + *q++ = i++; + break; + default: + BUG(); + } } /* Assumptions: the head and tail of inbuf are ours to play with. From 496d6c32d4d057cb44272d9bd587ff97d023ee92 Mon Sep 17 00:00:00 2001 From: Neil Brown Date: Thu, 8 May 2008 13:03:09 +1000 Subject: [PATCH 19/51] nfsd: fix spurious EACCESS in reconnect_path() Thanks to Frank Van Maarseveen for the original problem report: "A privileged process on an NFS client which drops privileges after using them to change the current working directory, will experience incorrect EACCES after an NFS server reboot. This problem can also occur after memory pressure on the server, particularly when the client side is quiet for some time." This occurs because the filehandle points to a directory whose parents are no longer in the dentry cache, and we're attempting to reconnect the directory to its parents without adequate permissions to perform lookups in the parent directories. We can therefore fix the problem by acquiring the necessary capabilities before attempting the reconnection. We do this only in the no_subtree_check case, since the documented behavior of the subtree_check export option requires the server to check that the user has lookup permissions on all parents. The subtree_check case still has a problem, since reconnect_path() unnecessarily requires both read and lookup permissions on all parent directories. However, a fix in that case would be more delicate, and use of subtree_check is already discouraged for other reasons. Signed-off-by: Neil Brown Cc: Frank van Maarseveen Signed-off-by: J. Bruce Fields --- fs/nfsd/nfsfh.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index c7b0fdaeac96..f45451eb1e38 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -176,9 +176,24 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) if (IS_ERR(exp)) return nfserrno(PTR_ERR(exp)); - error = nfsd_setuser_and_check_port(rqstp, exp); - if (error) - goto out; + if (exp->ex_flags & NFSEXP_NOSUBTREECHECK) { + /* Elevate privileges so that the lack of 'r' or 'x' + * permission on some parent directory will + * not stop exportfs_decode_fh from being able + * to reconnect a directory into the dentry cache. + * The same problem can affect "SUBTREECHECK" exports, + * but as nfsd_acceptable depends on correct + * access control settings being in effect, we cannot + * fix that case easily. + */ + current->cap_effective = + cap_raise_nfsd_set(current->cap_effective, + current->cap_permitted); + } else { + error = nfsd_setuser_and_check_port(rqstp, exp); + if (error) + goto out; + } /* * Look up the dentry using the NFS file handle. @@ -215,6 +230,14 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) goto out; } + if (exp->ex_flags & NFSEXP_NOSUBTREECHECK) { + error = nfsd_setuser_and_check_port(rqstp, exp); + if (error) { + dput(dentry); + goto out; + } + } + if (S_ISDIR(dentry->d_inode->i_mode) && (dentry->d_flags & DCACHE_DISCONNECTED)) { printk("nfsd: find_fh_dentry returned a DISCONNECTED directory: %s/%s\n", From 007de8b4fdd4f3f8ef9891f20b5dc03cf693bb5f Mon Sep 17 00:00:00 2001 From: James Lentini Date: Mon, 2 Jun 2008 15:33:59 -0400 Subject: [PATCH 20/51] update NFS/RDMA documentation Update the NFS/RDMA documentation to clarify how to run mount.nfs. Signed-off-by: James Lentini Signed-off-by: J. Bruce Fields --- Documentation/filesystems/nfs-rdma.txt | 75 +++++++++++++++----------- 1 file changed, 44 insertions(+), 31 deletions(-) diff --git a/Documentation/filesystems/nfs-rdma.txt b/Documentation/filesystems/nfs-rdma.txt index d0ec45ae4e7d..9ad453d4891a 100644 --- a/Documentation/filesystems/nfs-rdma.txt +++ b/Documentation/filesystems/nfs-rdma.txt @@ -5,7 +5,7 @@ ################################################################################ Author: NetApp and Open Grid Computing - Date: April 15, 2008 + Date: May 29, 2008 Table of Contents ~~~~~~~~~~~~~~~~~ @@ -60,16 +60,18 @@ Installation The procedures described in this document have been tested with distributions from Red Hat's Fedora Project (http://fedora.redhat.com/). - - Install nfs-utils-1.1.1 or greater on the client + - Install nfs-utils-1.1.2 or greater on the client - An NFS/RDMA mount point can only be obtained by using the mount.nfs - command in nfs-utils-1.1.1 or greater. To see which version of mount.nfs - you are using, type: + An NFS/RDMA mount point can be obtained by using the mount.nfs command in + nfs-utils-1.1.2 or greater (nfs-utils-1.1.1 was the first nfs-utils version + with support for NFS/RDMA mounts, but for various reasons we recommend using + nfs-utils-1.1.2 or greater). To see which version of mount.nfs you are + using, type: - > /sbin/mount.nfs -V + $ /sbin/mount.nfs -V - If the version is less than 1.1.1 or the command does not exist, - then you will need to install the latest version of nfs-utils. + If the version is less than 1.1.2 or the command does not exist, + you should install the latest version of nfs-utils. Download the latest package from: @@ -77,22 +79,32 @@ Installation Uncompress the package and follow the installation instructions. - If you will not be using GSS and NFSv4, the installation process - can be simplified by disabling these features when running configure: + If you will not need the idmapper and gssd executables (you do not need + these to create an NFS/RDMA enabled mount command), the installation + process can be simplified by disabling these features when running + configure: - > ./configure --disable-gss --disable-nfsv4 + $ ./configure --disable-gss --disable-nfsv4 - For more information on this see the package's README and INSTALL files. + To build nfs-utils you will need the tcp_wrappers package installed. For + more information on this see the package's README and INSTALL files. After building the nfs-utils package, there will be a mount.nfs binary in the utils/mount directory. This binary can be used to initiate NFS v2, v3, or v4 mounts. To initiate a v4 mount, the binary must be called mount.nfs4. The standard technique is to create a symlink called mount.nfs4 to mount.nfs. - NOTE: mount.nfs and therefore nfs-utils-1.1.1 or greater is only needed + This mount.nfs binary should be installed at /sbin/mount.nfs as follows: + + $ sudo cp utils/mount/mount.nfs /sbin/mount.nfs + + In this location, mount.nfs will be invoked automatically for NFS mounts + by the system mount commmand. + + NOTE: mount.nfs and therefore nfs-utils-1.1.2 or greater is only needed on the NFS client machine. You do not need this specific version of nfs-utils on the server. Furthermore, only the mount.nfs command from - nfs-utils-1.1.1 is needed on the client. + nfs-utils-1.1.2 is needed on the client. - Install a Linux kernel with NFS/RDMA @@ -156,8 +168,8 @@ Check RDMA and NFS Setup this time. For example, if you are using a Mellanox Tavor/Sinai/Arbel card: - > modprobe ib_mthca - > modprobe ib_ipoib + $ modprobe ib_mthca + $ modprobe ib_ipoib If you are using InfiniBand, make sure there is a Subnet Manager (SM) running on the network. If your IB switch has an embedded SM, you can @@ -166,7 +178,7 @@ Check RDMA and NFS Setup If an SM is running on your network, you should see the following: - > cat /sys/class/infiniband/driverX/ports/1/state + $ cat /sys/class/infiniband/driverX/ports/1/state 4: ACTIVE where driverX is mthca0, ipath5, ehca3, etc. @@ -174,10 +186,10 @@ Check RDMA and NFS Setup To further test the InfiniBand software stack, use IPoIB (this assumes you have two IB hosts named host1 and host2): - host1> ifconfig ib0 a.b.c.x - host2> ifconfig ib0 a.b.c.y - host1> ping a.b.c.y - host2> ping a.b.c.x + host1$ ifconfig ib0 a.b.c.x + host2$ ifconfig ib0 a.b.c.y + host1$ ping a.b.c.y + host2$ ping a.b.c.x For other device types, follow the appropriate procedures. @@ -214,9 +226,9 @@ NFS/RDMA Setup For InfiniBand using a Mellanox adapter: - > modprobe ib_mthca - > modprobe ib_ipoib - > ifconfig ib0 a.b.c.d + $ modprobe ib_mthca + $ modprobe ib_ipoib + $ ifconfig ib0 a.b.c.d NOTE: use unique addresses for the client and server @@ -225,30 +237,31 @@ NFS/RDMA Setup If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in kernel config), load the RDMA transport module: - > modprobe svcrdma + $ modprobe svcrdma Regardless of how the server was built (module or built-in), start the server: - > /etc/init.d/nfs start + $ /etc/init.d/nfs start or - > service nfs start + $ service nfs start Instruct the server to listen on the RDMA transport: - > echo rdma 2050 > /proc/fs/nfsd/portlist + $ echo rdma 2050 > /proc/fs/nfsd/portlist - On the client system If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in kernel config), load the RDMA client module: - > modprobe xprtrdma.ko + $ modprobe xprtrdma.ko - Regardless of how the client was built (module or built-in), issue the mount.nfs command: + Regardless of how the client was built (module or built-in), use this command to + mount the NFS/RDMA server: - > /path/to/your/mount.nfs :/ /mnt -i -o rdma,port=2050 + $ mount -o rdma,port=2050 :/ /mnt To verify that the mount is using RDMA, run "cat /proc/mounts" and check the "proto" field for the given mount. From 3cd2cfeae187fb754f9530e3f919256f350e89ca Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 2 Jun 2008 16:01:51 -0400 Subject: [PATCH 21/51] nfs: rewrap NFS/RDMA documentation to 80 lines Wrap long lines. Signed-off-by: J. Bruce Fields --- Documentation/filesystems/nfs-rdma.txt | 40 ++++++++++++++------------ 1 file changed, 21 insertions(+), 19 deletions(-) diff --git a/Documentation/filesystems/nfs-rdma.txt b/Documentation/filesystems/nfs-rdma.txt index 9ad453d4891a..44bd766f2e5d 100644 --- a/Documentation/filesystems/nfs-rdma.txt +++ b/Documentation/filesystems/nfs-rdma.txt @@ -63,10 +63,10 @@ Installation - Install nfs-utils-1.1.2 or greater on the client An NFS/RDMA mount point can be obtained by using the mount.nfs command in - nfs-utils-1.1.2 or greater (nfs-utils-1.1.1 was the first nfs-utils version - with support for NFS/RDMA mounts, but for various reasons we recommend using - nfs-utils-1.1.2 or greater). To see which version of mount.nfs you are - using, type: + nfs-utils-1.1.2 or greater (nfs-utils-1.1.1 was the first nfs-utils + version with support for NFS/RDMA mounts, but for various reasons we + recommend using nfs-utils-1.1.2 or greater). To see which version of + mount.nfs you are using, type: $ /sbin/mount.nfs -V @@ -91,8 +91,9 @@ Installation After building the nfs-utils package, there will be a mount.nfs binary in the utils/mount directory. This binary can be used to initiate NFS v2, v3, - or v4 mounts. To initiate a v4 mount, the binary must be called mount.nfs4. - The standard technique is to create a symlink called mount.nfs4 to mount.nfs. + or v4 mounts. To initiate a v4 mount, the binary must be called + mount.nfs4. The standard technique is to create a symlink called + mount.nfs4 to mount.nfs. This mount.nfs binary should be installed at /sbin/mount.nfs as follows: @@ -214,11 +215,11 @@ NFS/RDMA Setup /vol0 192.168.0.47(fsid=0,rw,async,insecure,no_root_squash) /vol0 192.168.0.0/255.255.255.0(fsid=0,rw,async,insecure,no_root_squash) - The IP address(es) is(are) the client's IPoIB address for an InfiniBand HCA or the - cleint's iWARP address(es) for an RNIC. + The IP address(es) is(are) the client's IPoIB address for an InfiniBand + HCA or the cleint's iWARP address(es) for an RNIC. - NOTE: The "insecure" option must be used because the NFS/RDMA client does not - use a reserved port. + NOTE: The "insecure" option must be used because the NFS/RDMA client does + not use a reserved port. Each time a machine boots: @@ -234,12 +235,13 @@ NFS/RDMA Setup - Start the NFS server - If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in kernel config), - load the RDMA transport module: + If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in + kernel config), load the RDMA transport module: $ modprobe svcrdma - Regardless of how the server was built (module or built-in), start the server: + Regardless of how the server was built (module or built-in), start the + server: $ /etc/init.d/nfs start @@ -253,17 +255,17 @@ NFS/RDMA Setup - On the client system - If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in kernel config), - load the RDMA client module: + If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in + kernel config), load the RDMA client module: $ modprobe xprtrdma.ko - Regardless of how the client was built (module or built-in), use this command to - mount the NFS/RDMA server: + Regardless of how the client was built (module or built-in), use this + command to mount the NFS/RDMA server: $ mount -o rdma,port=2050 :/ /mnt - To verify that the mount is using RDMA, run "cat /proc/mounts" and check the - "proto" field for the given mount. + To verify that the mount is using RDMA, run "cat /proc/mounts" and check + the "proto" field for the given mount. Congratulations! You're using NFS/RDMA! From 100766f8347c1aeb5a548c5c7aa9012f4a3276f1 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 30 Jun 2008 14:09:46 -0400 Subject: [PATCH 22/51] nfsd: treat all shutdown signals as equivalent knfsd currently uses 2 signal masks when processing requests. A "loose" mask (SHUTDOWN_SIGS) that it uses when receiving network requests, and then a more "strict" mask (ALLOWED_SIGS, which is just SIGKILL) that it allows when doing the actual operation on the local storage. This is apparently unnecessarily complicated. The underlying filesystem should be able to sanely handle a signal in the middle of an operation. This patch removes the signal mask handling from knfsd altogether. When knfsd is started as a kthread, all signals are ignored. It then allows all of the signals in SHUTDOWN_SIGS. There's no need to set the mask as well. Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfssvc.c | 30 +++++------------------------- 1 file changed, 5 insertions(+), 25 deletions(-) diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 96fdbcab8d95..80292ff5e924 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -37,15 +37,6 @@ #define NFSDDBG_FACILITY NFSDDBG_SVC -/* these signals will be delivered to an nfsd thread - * when handling a request - */ -#define ALLOWED_SIGS (sigmask(SIGKILL)) -/* these signals will be delivered to an nfsd thread - * when not handling a request. i.e. when waiting - */ -#define SHUTDOWN_SIGS (sigmask(SIGKILL) | sigmask(SIGHUP) | sigmask(SIGINT) | sigmask(SIGQUIT)) - extern struct svc_program nfsd_program; static int nfsd(void *vrqstp); struct timeval nfssvc_boot; @@ -414,9 +405,7 @@ nfsd(void *vrqstp) { struct svc_rqst *rqstp = (struct svc_rqst *) vrqstp; struct fs_struct *fsp; - sigset_t shutdown_mask, allowed_mask; int err, preverr = 0; - unsigned int signo; /* Lock module and set up kernel thread */ mutex_lock(&nfsd_mutex); @@ -433,17 +422,14 @@ nfsd(void *vrqstp) current->fs = fsp; current->fs->umask = 0; - siginitsetinv(&shutdown_mask, SHUTDOWN_SIGS); - siginitsetinv(&allowed_mask, ALLOWED_SIGS); - /* * thread is spawned with all signals set to SIG_IGN, re-enable - * the ones that matter + * the ones that will bring down the thread */ - for (signo = 1; signo <= _NSIG; signo++) { - if (!sigismember(&shutdown_mask, signo)) - allow_signal(signo); - } + allow_signal(SIGKILL); + allow_signal(SIGHUP); + allow_signal(SIGINT); + allow_signal(SIGQUIT); nfsdstats.th_cnt++; mutex_unlock(&nfsd_mutex); @@ -460,9 +446,6 @@ nfsd(void *vrqstp) * The main request loop */ for (;;) { - /* Block all but the shutdown signals */ - sigprocmask(SIG_SETMASK, &shutdown_mask, NULL); - /* * Find a socket with data available and call its * recvfrom routine. @@ -487,9 +470,6 @@ nfsd(void *vrqstp) /* Lock the export hash tables for reading. */ exp_readlock(); - /* Process request with signals blocked. */ - sigprocmask(SIG_SETMASK, &allowed_mask, NULL); - svc_process(rqstp); /* Unlock export hash tables */ From 07cad1d2a4b0112acd41381d5bc6be82fd71ebac Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 1 Jul 2008 15:38:35 +0200 Subject: [PATCH 23/51] nfsd: clean up mnt_want_write calls Multiple mnt_want_write() calls in the switch statement looks really ugly. Signed-off-by: Miklos Szeredi Acked-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- fs/nfsd/vfs.c | 25 +++++++++++-------------- 1 file changed, 11 insertions(+), 14 deletions(-) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 5e05ddda4560..0f4481e0502d 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1250,36 +1250,34 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, iap->ia_mode = 0; iap->ia_mode = (iap->ia_mode & S_IALLUGO) | type; + err = nfserr_inval; + if (!S_ISREG(type) && !S_ISDIR(type) && !special_file(type)) { + printk(KERN_WARNING "nfsd: bad file type %o in nfsd_create\n", + type); + goto out; + } + + host_err = mnt_want_write(fhp->fh_export->ex_path.mnt); + if (host_err) + goto out_nfserr; + /* * Get the dir op function pointer. */ err = 0; switch (type) { case S_IFREG: - host_err = mnt_want_write(fhp->fh_export->ex_path.mnt); - if (host_err) - goto out_nfserr; host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL); break; case S_IFDIR: - host_err = mnt_want_write(fhp->fh_export->ex_path.mnt); - if (host_err) - goto out_nfserr; host_err = vfs_mkdir(dirp, dchild, iap->ia_mode); break; case S_IFCHR: case S_IFBLK: case S_IFIFO: case S_IFSOCK: - host_err = mnt_want_write(fhp->fh_export->ex_path.mnt); - if (host_err) - goto out_nfserr; host_err = vfs_mknod(dirp, dchild, iap->ia_mode, rdev); break; - default: - printk("nfsd: bad file type %o in nfsd_create\n", type); - host_err = -EINVAL; - goto out_nfserr; } if (host_err < 0) { mnt_drop_write(fhp->fh_export->ex_path.mnt); @@ -1291,7 +1289,6 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, write_inode_now(dchild->d_inode, 1); } - err2 = nfsd_create_setattr(rqstp, resfhp, iap); if (err2) err = err2; From 30cff1ffff3981c8d96dc33870b652e70190ba37 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Wed, 2 Jul 2008 11:13:18 +0300 Subject: [PATCH 24/51] nfsd: return nfserr_minor_vers_mismatch when compound minorversion != 0 Check minorversion once before decoding any operation and reject with nfserr_minor_vers_mismatch if != 0 (this still happens in nfsd4_proc_compound). In this case return a zero length resultdata array as required by RFC3530. minorversion 1 processing will have its own vector of decoders. Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 9547ab636274..413a15332177 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1019,6 +1019,9 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) } } + if (argp->minorversion != 0) + argp->opcnt = 0; + for (i = 0; i < argp->opcnt; i++) { op = &argp->ops[i]; op->replay = NULL; @@ -1057,13 +1060,6 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) op->opnum = ntohl(*argp->p++); switch (op->opnum) { - case 2: /* Reserved operation */ - op->opnum = OP_ILLEGAL; - if (argp->minorversion == 0) - op->status = nfserr_op_illegal; - else - op->status = nfserr_minor_vers_mismatch; - break; case OP_ACCESS: op->status = nfsd4_decode_access(argp, &op->u.access); break; From 347e0ad9c91b5bd7506d61f236048cc72b7fc151 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Wed, 2 Jul 2008 11:13:41 +0300 Subject: [PATCH 25/51] nfsd: tabulate nfs4 xdr decoding functions In preparation for minorversion 1 Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 153 +++++++++++++++------------------------------- 1 file changed, 48 insertions(+), 105 deletions(-) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 413a15332177..de1fd9db26f0 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -985,6 +985,51 @@ nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_rel DECODE_TAIL; } +static __be32 +nfsd4_decode_noop(struct nfsd4_compoundargs *argp, void *p) +{ + return nfs_ok; +} + +typedef __be32(*nfsd4_dec)(struct nfsd4_compoundargs *argp, void *); + +static nfsd4_dec nfsd4_dec_ops[] = { + [OP_ACCESS] (nfsd4_dec)nfsd4_decode_access, + [OP_CLOSE] (nfsd4_dec)nfsd4_decode_close, + [OP_COMMIT] (nfsd4_dec)nfsd4_decode_commit, + [OP_CREATE] (nfsd4_dec)nfsd4_decode_create, + [OP_DELEGRETURN] (nfsd4_dec)nfsd4_decode_delegreturn, + [OP_GETATTR] (nfsd4_dec)nfsd4_decode_getattr, + [OP_GETFH] (nfsd4_dec)nfsd4_decode_noop, + [OP_LINK] (nfsd4_dec)nfsd4_decode_link, + [OP_LOCK] (nfsd4_dec)nfsd4_decode_lock, + [OP_LOCKT] (nfsd4_dec)nfsd4_decode_lockt, + [OP_LOCKU] (nfsd4_dec)nfsd4_decode_locku, + [OP_LOOKUP] (nfsd4_dec)nfsd4_decode_lookup, + [OP_LOOKUPP] (nfsd4_dec)nfsd4_decode_noop, + [OP_NVERIFY] (nfsd4_dec)nfsd4_decode_verify, + [OP_OPEN] (nfsd4_dec)nfsd4_decode_open, + [OP_OPEN_CONFIRM] (nfsd4_dec)nfsd4_decode_open_confirm, + [OP_OPEN_DOWNGRADE] (nfsd4_dec)nfsd4_decode_open_downgrade, + [OP_PUTFH] (nfsd4_dec)nfsd4_decode_putfh, + [OP_PUTROOTFH] (nfsd4_dec)nfsd4_decode_noop, + [OP_READ] (nfsd4_dec)nfsd4_decode_read, + [OP_READDIR] (nfsd4_dec)nfsd4_decode_readdir, + [OP_READLINK] (nfsd4_dec)nfsd4_decode_noop, + [OP_REMOVE] (nfsd4_dec)nfsd4_decode_remove, + [OP_RENAME] (nfsd4_dec)nfsd4_decode_rename, + [OP_RENEW] (nfsd4_dec)nfsd4_decode_renew, + [OP_RESTOREFH] (nfsd4_dec)nfsd4_decode_noop, + [OP_SAVEFH] (nfsd4_dec)nfsd4_decode_noop, + [OP_SECINFO] (nfsd4_dec)nfsd4_decode_secinfo, + [OP_SETATTR] (nfsd4_dec)nfsd4_decode_setattr, + [OP_SETCLIENTID] (nfsd4_dec)nfsd4_decode_setclientid, + [OP_SETCLIENTID_CONFIRM](nfsd4_dec)nfsd4_decode_setclientid_confirm, + [OP_VERIFY] (nfsd4_dec)nfsd4_decode_verify, + [OP_WRITE] (nfsd4_dec)nfsd4_decode_write, + [OP_RELEASE_LOCKOWNER] (nfsd4_dec)nfsd4_decode_release_lockowner, +}; + static __be32 nfsd4_decode_compound(struct nfsd4_compoundargs *argp) { @@ -1059,113 +1104,11 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) } op->opnum = ntohl(*argp->p++); - switch (op->opnum) { - case OP_ACCESS: - op->status = nfsd4_decode_access(argp, &op->u.access); - break; - case OP_CLOSE: - op->status = nfsd4_decode_close(argp, &op->u.close); - break; - case OP_COMMIT: - op->status = nfsd4_decode_commit(argp, &op->u.commit); - break; - case OP_CREATE: - op->status = nfsd4_decode_create(argp, &op->u.create); - break; - case OP_DELEGRETURN: - op->status = nfsd4_decode_delegreturn(argp, &op->u.delegreturn); - break; - case OP_GETATTR: - op->status = nfsd4_decode_getattr(argp, &op->u.getattr); - break; - case OP_GETFH: - op->status = nfs_ok; - break; - case OP_LINK: - op->status = nfsd4_decode_link(argp, &op->u.link); - break; - case OP_LOCK: - op->status = nfsd4_decode_lock(argp, &op->u.lock); - break; - case OP_LOCKT: - op->status = nfsd4_decode_lockt(argp, &op->u.lockt); - break; - case OP_LOCKU: - op->status = nfsd4_decode_locku(argp, &op->u.locku); - break; - case OP_LOOKUP: - op->status = nfsd4_decode_lookup(argp, &op->u.lookup); - break; - case OP_LOOKUPP: - op->status = nfs_ok; - break; - case OP_NVERIFY: - op->status = nfsd4_decode_verify(argp, &op->u.nverify); - break; - case OP_OPEN: - op->status = nfsd4_decode_open(argp, &op->u.open); - break; - case OP_OPEN_CONFIRM: - op->status = nfsd4_decode_open_confirm(argp, &op->u.open_confirm); - break; - case OP_OPEN_DOWNGRADE: - op->status = nfsd4_decode_open_downgrade(argp, &op->u.open_downgrade); - break; - case OP_PUTFH: - op->status = nfsd4_decode_putfh(argp, &op->u.putfh); - break; - case OP_PUTROOTFH: - op->status = nfs_ok; - break; - case OP_READ: - op->status = nfsd4_decode_read(argp, &op->u.read); - break; - case OP_READDIR: - op->status = nfsd4_decode_readdir(argp, &op->u.readdir); - break; - case OP_READLINK: - op->status = nfs_ok; - break; - case OP_REMOVE: - op->status = nfsd4_decode_remove(argp, &op->u.remove); - break; - case OP_RENAME: - op->status = nfsd4_decode_rename(argp, &op->u.rename); - break; - case OP_RESTOREFH: - op->status = nfs_ok; - break; - case OP_RENEW: - op->status = nfsd4_decode_renew(argp, &op->u.renew); - break; - case OP_SAVEFH: - op->status = nfs_ok; - break; - case OP_SECINFO: - op->status = nfsd4_decode_secinfo(argp, &op->u.secinfo); - break; - case OP_SETATTR: - op->status = nfsd4_decode_setattr(argp, &op->u.setattr); - break; - case OP_SETCLIENTID: - op->status = nfsd4_decode_setclientid(argp, &op->u.setclientid); - break; - case OP_SETCLIENTID_CONFIRM: - op->status = nfsd4_decode_setclientid_confirm(argp, &op->u.setclientid_confirm); - break; - case OP_VERIFY: - op->status = nfsd4_decode_verify(argp, &op->u.verify); - break; - case OP_WRITE: - op->status = nfsd4_decode_write(argp, &op->u.write); - break; - case OP_RELEASE_LOCKOWNER: - op->status = nfsd4_decode_release_lockowner(argp, &op->u.release_lockowner); - break; - default: + if (op->opnum >= OP_ACCESS && op->opnum < ARRAY_SIZE(nfsd4_dec_ops)) + op->status = nfsd4_dec_ops[op->opnum](argp, &op->u); + else { op->opnum = OP_ILLEGAL; op->status = nfserr_op_illegal; - break; } if (op->status) { From 3c375c6f3a809d0d999d6dc933634f0b97ed7ae9 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Wed, 2 Jul 2008 11:14:01 +0300 Subject: [PATCH 26/51] nfsd: unsupported nfs4 ops should fail with nfserr_opnotsupp nfserr_opnotsupp should be returned for unsupported nfs4 ops rather than nfserr_op_illegal. Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index de1fd9db26f0..653951c73e31 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -991,6 +991,12 @@ nfsd4_decode_noop(struct nfsd4_compoundargs *argp, void *p) return nfs_ok; } +static __be32 +nfsd4_decode_notsupp(struct nfsd4_compoundargs *argp, void *p) +{ + return nfserr_opnotsupp; +} + typedef __be32(*nfsd4_dec)(struct nfsd4_compoundargs *argp, void *); static nfsd4_dec nfsd4_dec_ops[] = { @@ -998,6 +1004,7 @@ static nfsd4_dec nfsd4_dec_ops[] = { [OP_CLOSE] (nfsd4_dec)nfsd4_decode_close, [OP_COMMIT] (nfsd4_dec)nfsd4_decode_commit, [OP_CREATE] (nfsd4_dec)nfsd4_decode_create, + [OP_DELEGPURGE] (nfsd4_dec)nfsd4_decode_notsupp, [OP_DELEGRETURN] (nfsd4_dec)nfsd4_decode_delegreturn, [OP_GETATTR] (nfsd4_dec)nfsd4_decode_getattr, [OP_GETFH] (nfsd4_dec)nfsd4_decode_noop, @@ -1009,9 +1016,11 @@ static nfsd4_dec nfsd4_dec_ops[] = { [OP_LOOKUPP] (nfsd4_dec)nfsd4_decode_noop, [OP_NVERIFY] (nfsd4_dec)nfsd4_decode_verify, [OP_OPEN] (nfsd4_dec)nfsd4_decode_open, + [OP_OPENATTR] (nfsd4_dec)nfsd4_decode_notsupp, [OP_OPEN_CONFIRM] (nfsd4_dec)nfsd4_decode_open_confirm, [OP_OPEN_DOWNGRADE] (nfsd4_dec)nfsd4_decode_open_downgrade, [OP_PUTFH] (nfsd4_dec)nfsd4_decode_putfh, + [OP_PUTPUBFH] (nfsd4_dec)nfsd4_decode_notsupp, [OP_PUTROOTFH] (nfsd4_dec)nfsd4_decode_noop, [OP_READ] (nfsd4_dec)nfsd4_decode_read, [OP_READDIR] (nfsd4_dec)nfsd4_decode_readdir, From f2feb96bc3d18e50cab7de9eab142f99d91aa5f6 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Wed, 2 Jul 2008 11:14:22 +0300 Subject: [PATCH 27/51] nfsd: nfs4 minorversion decoder vectors Have separate vectors of operation decoders for each minorversion. Obsolete ops in newer minorversions have default implementation returning nfserr_opnotsupp. Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 653951c73e31..a40bec53fa66 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1039,11 +1039,21 @@ static nfsd4_dec nfsd4_dec_ops[] = { [OP_RELEASE_LOCKOWNER] (nfsd4_dec)nfsd4_decode_release_lockowner, }; +struct nfsd4_minorversion_ops { + nfsd4_dec *decoders; + int nops; +}; + +static struct nfsd4_minorversion_ops nfsd4_minorversion[] = { + [0] { nfsd4_dec_ops, ARRAY_SIZE(nfsd4_dec_ops) }, +}; + static __be32 nfsd4_decode_compound(struct nfsd4_compoundargs *argp) { DECODE_HEAD; struct nfsd4_op *op; + struct nfsd4_minorversion_ops *ops; int i; /* @@ -1073,9 +1083,10 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) } } - if (argp->minorversion != 0) + if (argp->minorversion >= ARRAY_SIZE(nfsd4_minorversion)) argp->opcnt = 0; + ops = &nfsd4_minorversion[argp->minorversion]; for (i = 0; i < argp->opcnt; i++) { op = &argp->ops[i]; op->replay = NULL; @@ -1113,8 +1124,8 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) } op->opnum = ntohl(*argp->p++); - if (op->opnum >= OP_ACCESS && op->opnum < ARRAY_SIZE(nfsd4_dec_ops)) - op->status = nfsd4_dec_ops[op->opnum](argp, &op->u); + if (op->opnum >= OP_ACCESS && op->opnum < ops->nops) + op->status = ops->decoders[op->opnum](argp, &op->u); else { op->opnum = OP_ILLEGAL; op->status = nfserr_op_illegal; From ab96dddbedf4bb8a7a0fe44012efc1d99598c36f Mon Sep 17 00:00:00 2001 From: Tom Tucker Date: Wed, 28 May 2008 13:54:04 -0500 Subject: [PATCH 28/51] svcrdma: Add a type for keeping NFS RPC mapping Create a new data structure to hold the remote client address space to local server address space mapping. Signed-off-by: Tom Tucker --- include/linux/sunrpc/svc_rdma.h | 27 ++++++++++++++++++++++++ net/sunrpc/xprtrdma/svc_rdma.c | 19 +++++++++++++++++ net/sunrpc/xprtrdma/svc_rdma_transport.c | 26 +++++++++++++++++++++++ 3 files changed, 72 insertions(+) diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 05eb4664d0dd..bd8749cc8084 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -86,6 +86,31 @@ struct svc_rdma_op_ctxt { struct page *pages[RPCSVC_MAXPAGES]; }; +/* + * NFS_ requests are mapped on the client side by the chunk lists in + * the RPCRDMA header. During the fetching of the RPC from the client + * and the writing of the reply to the client, the memory in the + * client and the memory in the server must be mapped as contiguous + * vaddr/len for access by the hardware. These data strucures keep + * these mappings. + * + * For an RDMA_WRITE, the 'sge' maps the RPC REPLY. For RDMA_READ, the + * 'sge' in the svc_rdma_req_map maps the server side RPC reply and the + * 'ch' field maps the read-list of the RPCRDMA header to the 'sge' + * mapping of the reply. + */ +struct svc_rdma_chunk_sge { + int start; /* sge no for this chunk */ + int count; /* sge count for this chunk */ +}; +struct svc_rdma_req_map { + unsigned long count; + union { + struct kvec sge[RPCSVC_MAXPAGES]; + struct svc_rdma_chunk_sge ch[RPCSVC_MAXPAGES]; + }; +}; + #define RDMACTXT_F_LAST_CTXT 2 struct svcxprt_rdma { @@ -173,6 +198,8 @@ extern int svc_rdma_post_recv(struct svcxprt_rdma *); extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *); extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *); extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int); +extern struct svc_rdma_req_map *svc_rdma_get_req_map(void); +extern void svc_rdma_put_req_map(struct svc_rdma_req_map *); extern void svc_sq_reap(struct svcxprt_rdma *); extern void svc_rq_reap(struct svcxprt_rdma *); extern struct svc_xprt_class svc_rdma_class; diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 88c0ca20bb1e..171f2053e90c 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -69,6 +69,9 @@ atomic_t rdma_stat_rq_prod; atomic_t rdma_stat_sq_poll; atomic_t rdma_stat_sq_prod; +/* Temporary NFS request map cache */ +struct kmem_cache *svc_rdma_map_cachep; + /* * This function implements reading and resetting an atomic_t stat * variable through read/write to a proc file. Any write to the file @@ -241,6 +244,7 @@ void svc_rdma_cleanup(void) svcrdma_table_header = NULL; } svc_unreg_xprt_class(&svc_rdma_class); + kmem_cache_destroy(svc_rdma_map_cachep); } int svc_rdma_init(void) @@ -255,9 +259,24 @@ int svc_rdma_init(void) svcrdma_table_header = register_sysctl_table(svcrdma_root_table); + /* Create the temporary map cache */ + svc_rdma_map_cachep = kmem_cache_create("svc_rdma_map_cache", + sizeof(struct svc_rdma_req_map), + 0, + SLAB_HWCACHE_ALIGN, + NULL); + if (!svc_rdma_map_cachep) { + printk(KERN_INFO "Could not allocate map cache.\n"); + goto err; + } + /* Register RDMA with the SVC transport switch */ svc_reg_xprt_class(&svc_rdma_class); return 0; + + err: + unregister_sysctl_table(svcrdma_table_header); + return -ENOMEM; } MODULE_AUTHOR("Tom Tucker "); MODULE_DESCRIPTION("SVC RDMA Transport"); diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index e132509d1db0..ae90758d8e9b 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -173,6 +173,32 @@ void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages) atomic_dec(&xprt->sc_ctxt_used); } +/* Temporary NFS request map cache. Created in svc_rdma.c */ +extern struct kmem_cache *svc_rdma_map_cachep; + +/* + * Temporary NFS req mappings are shared across all transport + * instances. These are short lived and should be bounded by the number + * of concurrent server threads * depth of the SQ. + */ +struct svc_rdma_req_map *svc_rdma_get_req_map(void) +{ + struct svc_rdma_req_map *map; + while (1) { + map = kmem_cache_alloc(svc_rdma_map_cachep, GFP_KERNEL); + if (map) + break; + schedule_timeout_uninterruptible(msecs_to_jiffies(500)); + } + map->count = 0; + return map; +} + +void svc_rdma_put_req_map(struct svc_rdma_req_map *map) +{ + kmem_cache_free(svc_rdma_map_cachep, map); +} + /* ib_cq event handler */ static void cq_event_handler(struct ib_event *event, void *context) { From 34d16e42a6ab74a4a4389c061dfa3c6609e08fa0 Mon Sep 17 00:00:00 2001 From: Tom Tucker Date: Wed, 2 Jul 2008 14:56:13 -0500 Subject: [PATCH 29/51] svcrdma: Use RPC reply map for RDMA_WRITE processing Use the new svc_rdma_req_map data type for mapping the client side memory to the server side memory. Move the DMA mapping to the context pointed to by each WR individually so that it is unmapped after the WR completes. Signed-off-by: Tom Tucker --- net/sunrpc/xprtrdma/svc_rdma_sendto.c | 163 +++++++++++------------ net/sunrpc/xprtrdma/svc_rdma_transport.c | 5 +- 2 files changed, 80 insertions(+), 88 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index fb82b1b683f8..bdc11a30e937 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -63,52 +63,44 @@ * SGE[2..sge_count-2] data from xdr->pages[] * SGE[sge_count-1] data from xdr->tail. * + * The max SGE we need is the length of the XDR / pagesize + one for + * head + one for tail + one for RPCRDMA header. Since RPCSVC_MAXPAGES + * reserves a page for both the request and the reply header, and this + * array is only concerned with the reply we are assured that we have + * on extra page for the RPCRMDA header. */ -static struct ib_sge *xdr_to_sge(struct svcxprt_rdma *xprt, - struct xdr_buf *xdr, - struct ib_sge *sge, - int *sge_count) +static void xdr_to_sge(struct svcxprt_rdma *xprt, + struct xdr_buf *xdr, + struct svc_rdma_req_map *vec) { - /* Max we need is the length of the XDR / pagesize + one for - * head + one for tail + one for RPCRDMA header - */ int sge_max = (xdr->len+PAGE_SIZE-1) / PAGE_SIZE + 3; int sge_no; - u32 byte_count = xdr->len; u32 sge_bytes; u32 page_bytes; - int page_off; + u32 page_off; int page_no; + BUG_ON(xdr->len != + (xdr->head[0].iov_len + xdr->page_len + xdr->tail[0].iov_len)); + /* Skip the first sge, this is for the RPCRDMA header */ sge_no = 1; /* Head SGE */ - sge[sge_no].addr = ib_dma_map_single(xprt->sc_cm_id->device, - xdr->head[0].iov_base, - xdr->head[0].iov_len, - DMA_TO_DEVICE); - sge_bytes = min_t(u32, byte_count, xdr->head[0].iov_len); - byte_count -= sge_bytes; - sge[sge_no].length = sge_bytes; - sge[sge_no].lkey = xprt->sc_phys_mr->lkey; + vec->sge[sge_no].iov_base = xdr->head[0].iov_base; + vec->sge[sge_no].iov_len = xdr->head[0].iov_len; sge_no++; /* pages SGE */ page_no = 0; page_bytes = xdr->page_len; page_off = xdr->page_base; - while (byte_count && page_bytes) { - sge_bytes = min_t(u32, byte_count, (PAGE_SIZE-page_off)); - sge[sge_no].addr = - ib_dma_map_page(xprt->sc_cm_id->device, - xdr->pages[page_no], page_off, - sge_bytes, DMA_TO_DEVICE); - sge_bytes = min(sge_bytes, page_bytes); - byte_count -= sge_bytes; + while (page_bytes) { + vec->sge[sge_no].iov_base = + page_address(xdr->pages[page_no]) + page_off; + sge_bytes = min_t(u32, page_bytes, (PAGE_SIZE - page_off)); page_bytes -= sge_bytes; - sge[sge_no].length = sge_bytes; - sge[sge_no].lkey = xprt->sc_phys_mr->lkey; + vec->sge[sge_no].iov_len = sge_bytes; sge_no++; page_no++; @@ -116,36 +108,24 @@ static struct ib_sge *xdr_to_sge(struct svcxprt_rdma *xprt, } /* Tail SGE */ - if (byte_count && xdr->tail[0].iov_len) { - sge[sge_no].addr = - ib_dma_map_single(xprt->sc_cm_id->device, - xdr->tail[0].iov_base, - xdr->tail[0].iov_len, - DMA_TO_DEVICE); - sge_bytes = min_t(u32, byte_count, xdr->tail[0].iov_len); - byte_count -= sge_bytes; - sge[sge_no].length = sge_bytes; - sge[sge_no].lkey = xprt->sc_phys_mr->lkey; + if (xdr->tail[0].iov_len) { + vec->sge[sge_no].iov_base = xdr->tail[0].iov_base; + vec->sge[sge_no].iov_len = xdr->tail[0].iov_len; sge_no++; } BUG_ON(sge_no > sge_max); - BUG_ON(byte_count != 0); - - *sge_count = sge_no; - return sge; + vec->count = sge_no; } - /* Assumptions: * - The specified write_len can be represented in sc_max_sge * PAGE_SIZE */ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, u32 rmr, u64 to, u32 xdr_off, int write_len, - struct ib_sge *xdr_sge, int sge_count) + struct svc_rdma_req_map *vec) { - struct svc_rdma_op_ctxt *tmp_sge_ctxt; struct ib_send_wr write_wr; struct ib_sge *sge; int xdr_sge_no; @@ -154,25 +134,23 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, int sge_off; int bc; struct svc_rdma_op_ctxt *ctxt; - int ret = 0; - BUG_ON(sge_count > RPCSVC_MAXPAGES); + BUG_ON(vec->count > RPCSVC_MAXPAGES); dprintk("svcrdma: RDMA_WRITE rmr=%x, to=%llx, xdr_off=%d, " - "write_len=%d, xdr_sge=%p, sge_count=%d\n", + "write_len=%d, vec->sge=%p, vec->count=%lu\n", rmr, (unsigned long long)to, xdr_off, - write_len, xdr_sge, sge_count); + write_len, vec->sge, vec->count); ctxt = svc_rdma_get_context(xprt); - ctxt->count = 0; - tmp_sge_ctxt = svc_rdma_get_context(xprt); - sge = tmp_sge_ctxt->sge; + ctxt->direction = DMA_TO_DEVICE; + sge = ctxt->sge; /* Find the SGE associated with xdr_off */ - for (bc = xdr_off, xdr_sge_no = 1; bc && xdr_sge_no < sge_count; + for (bc = xdr_off, xdr_sge_no = 1; bc && xdr_sge_no < vec->count; xdr_sge_no++) { - if (xdr_sge[xdr_sge_no].length > bc) + if (vec->sge[xdr_sge_no].iov_len > bc) break; - bc -= xdr_sge[xdr_sge_no].length; + bc -= vec->sge[xdr_sge_no].iov_len; } sge_off = bc; @@ -180,21 +158,27 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, sge_no = 0; /* Copy the remaining SGE */ - while (bc != 0 && xdr_sge_no < sge_count) { - sge[sge_no].addr = xdr_sge[xdr_sge_no].addr + sge_off; - sge[sge_no].lkey = xdr_sge[xdr_sge_no].lkey; + while (bc != 0 && xdr_sge_no < vec->count) { + sge[sge_no].lkey = xprt->sc_phys_mr->lkey; sge_bytes = min((size_t)bc, - (size_t)(xdr_sge[xdr_sge_no].length-sge_off)); + (size_t)(vec->sge[xdr_sge_no].iov_len-sge_off)); sge[sge_no].length = sge_bytes; - + sge[sge_no].addr = + ib_dma_map_single(xprt->sc_cm_id->device, + (void *) + vec->sge[xdr_sge_no].iov_base + sge_off, + sge_bytes, DMA_TO_DEVICE); + if (dma_mapping_error(sge[sge_no].addr)) + goto err; sge_off = 0; sge_no++; + ctxt->count++; xdr_sge_no++; bc -= sge_bytes; } BUG_ON(bc != 0); - BUG_ON(xdr_sge_no > sge_count); + BUG_ON(xdr_sge_no > vec->count); /* Prepare WRITE WR */ memset(&write_wr, 0, sizeof write_wr); @@ -209,21 +193,20 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, /* Post It */ atomic_inc(&rdma_stat_write); - if (svc_rdma_send(xprt, &write_wr)) { - svc_rdma_put_context(ctxt, 1); - /* Fatal error, close transport */ - ret = -EIO; - } - svc_rdma_put_context(tmp_sge_ctxt, 0); - return ret; + if (svc_rdma_send(xprt, &write_wr)) + goto err; + return 0; + err: + svc_rdma_put_context(ctxt, 0); + /* Fatal error, close transport */ + return -EIO; } static int send_write_chunks(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rdma_argp, struct rpcrdma_msg *rdma_resp, struct svc_rqst *rqstp, - struct ib_sge *sge, - int sge_count) + struct svc_rdma_req_map *vec) { u32 xfer_len = rqstp->rq_res.page_len + rqstp->rq_res.tail[0].iov_len; int write_len; @@ -269,8 +252,7 @@ static int send_write_chunks(struct svcxprt_rdma *xprt, rs_offset + chunk_off, xdr_off, this_write, - sge, - sge_count); + vec); if (ret) { dprintk("svcrdma: RDMA_WRITE failed, ret=%d\n", ret); @@ -292,8 +274,7 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rdma_argp, struct rpcrdma_msg *rdma_resp, struct svc_rqst *rqstp, - struct ib_sge *sge, - int sge_count) + struct svc_rdma_req_map *vec) { u32 xfer_len = rqstp->rq_res.len; int write_len; @@ -341,8 +322,7 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt, rs_offset + chunk_off, xdr_off, this_write, - sge, - sge_count); + vec); if (ret) { dprintk("svcrdma: RDMA_WRITE failed, ret=%d\n", ret); @@ -380,7 +360,7 @@ static int send_reply(struct svcxprt_rdma *rdma, struct page *page, struct rpcrdma_msg *rdma_resp, struct svc_rdma_op_ctxt *ctxt, - int sge_count, + struct svc_rdma_req_map *vec, int byte_count) { struct ib_send_wr send_wr; @@ -413,10 +393,15 @@ static int send_reply(struct svcxprt_rdma *rdma, ctxt->sge[0].lkey = rdma->sc_phys_mr->lkey; /* Determine how many of our SGE are to be transmitted */ - for (sge_no = 1; byte_count && sge_no < sge_count; sge_no++) { - sge_bytes = min((size_t)ctxt->sge[sge_no].length, - (size_t)byte_count); + for (sge_no = 1; byte_count && sge_no < vec->count; sge_no++) { + sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count); byte_count -= sge_bytes; + ctxt->sge[sge_no].addr = + ib_dma_map_single(rdma->sc_cm_id->device, + vec->sge[sge_no].iov_base, + sge_bytes, DMA_TO_DEVICE); + ctxt->sge[sge_no].length = sge_bytes; + ctxt->sge[sge_no].lkey = rdma->sc_phys_mr->lkey; } BUG_ON(byte_count != 0); @@ -428,8 +413,10 @@ static int send_reply(struct svcxprt_rdma *rdma, ctxt->pages[page_no+1] = rqstp->rq_respages[page_no]; ctxt->count++; rqstp->rq_respages[page_no] = NULL; + /* If there are more pages than SGE, terminate SGE list */ + if (page_no+1 >= sge_no) + ctxt->sge[page_no+1].length = 0; } - BUG_ON(sge_no > rdma->sc_max_sge); memset(&send_wr, 0, sizeof send_wr); ctxt->wr_op = IB_WR_SEND; @@ -473,20 +460,20 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) enum rpcrdma_proc reply_type; int ret; int inline_bytes; - struct ib_sge *sge; - int sge_count = 0; struct page *res_page; struct svc_rdma_op_ctxt *ctxt; + struct svc_rdma_req_map *vec; dprintk("svcrdma: sending response for rqstp=%p\n", rqstp); /* Get the RDMA request header. */ rdma_argp = xdr_start(&rqstp->rq_arg); - /* Build an SGE for the XDR */ + /* Build an req vec for the XDR */ ctxt = svc_rdma_get_context(rdma); ctxt->direction = DMA_TO_DEVICE; - sge = xdr_to_sge(rdma, &rqstp->rq_res, ctxt->sge, &sge_count); + vec = svc_rdma_get_req_map(); + xdr_to_sge(rdma, &rqstp->rq_res, vec); inline_bytes = rqstp->rq_res.len; @@ -503,7 +490,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) /* Send any write-chunk data and build resp write-list */ ret = send_write_chunks(rdma, rdma_argp, rdma_resp, - rqstp, sge, sge_count); + rqstp, vec); if (ret < 0) { printk(KERN_ERR "svcrdma: failed to send write chunks, rc=%d\n", ret); @@ -513,7 +500,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) /* Send any reply-list data and update resp reply-list */ ret = send_reply_chunks(rdma, rdma_argp, rdma_resp, - rqstp, sge, sge_count); + rqstp, vec); if (ret < 0) { printk(KERN_ERR "svcrdma: failed to send reply chunks, rc=%d\n", ret); @@ -521,11 +508,13 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) } inline_bytes -= ret; - ret = send_reply(rdma, rqstp, res_page, rdma_resp, ctxt, sge_count, + ret = send_reply(rdma, rqstp, res_page, rdma_resp, ctxt, vec, inline_bytes); + svc_rdma_put_req_map(vec); dprintk("svcrdma: send_reply returns %d\n", ret); return ret; error: + svc_rdma_put_req_map(vec); svc_rdma_put_context(ctxt, 0); put_page(res_page); return ret; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index ae90758d8e9b..fc86338bcbb2 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -387,10 +387,13 @@ static void sq_cq_reap(struct svcxprt_rdma *xprt) switch (ctxt->wr_op) { case IB_WR_SEND: - case IB_WR_RDMA_WRITE: svc_rdma_put_context(ctxt, 1); break; + case IB_WR_RDMA_WRITE: + svc_rdma_put_context(ctxt, 0); + break; + case IB_WR_RDMA_READ: if (test_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags)) { struct svc_rdma_op_ctxt *read_hdr = ctxt->read_hdr; From f820c57ebf5493d4602cc00577c8b0fadd27a7b8 Mon Sep 17 00:00:00 2001 From: Tom Tucker Date: Tue, 27 May 2008 17:03:14 -0500 Subject: [PATCH 30/51] svcrdma: Use reply and chunk map for RDMA_READ processing Modify the RDMA_READ processing to use the reply and chunk list mapping data types. Also add a special purpose 'hdr_count' field in in the context to hold the header page count instead of overloading the SGE length field and corrupting the DMA map length. Signed-off-by: Tom Tucker --- include/linux/sunrpc/svc_rdma.h | 1 + net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 83 +++++++++++-------------- 2 files changed, 39 insertions(+), 45 deletions(-) diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index bd8749cc8084..fd5e8a1c17de 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -72,6 +72,7 @@ extern atomic_t rdma_stat_sq_prod; */ struct svc_rdma_op_ctxt { struct svc_rdma_op_ctxt *read_hdr; + int hdr_count; struct list_head free_list; struct xdr_buf arg; struct list_head dto_q; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 06ab4841537b..d25971b42a74 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -112,11 +112,6 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, rqstp->rq_arg.tail[0].iov_len = 0; } -struct chunk_sge { - int start; /* sge no for this chunk */ - int count; /* sge count for this chunk */ -}; - /* Encode a read-chunk-list as an array of IB SGE * * Assumptions: @@ -134,8 +129,8 @@ static int rdma_rcl_to_sge(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *head, struct rpcrdma_msg *rmsgp, - struct ib_sge *sge, - struct chunk_sge *ch_sge_ary, + struct svc_rdma_req_map *rpl_map, + struct svc_rdma_req_map *chl_map, int ch_count, int byte_count) { @@ -156,22 +151,18 @@ static int rdma_rcl_to_sge(struct svcxprt_rdma *xprt, head->arg.head[0] = rqstp->rq_arg.head[0]; head->arg.tail[0] = rqstp->rq_arg.tail[0]; head->arg.pages = &head->pages[head->count]; - head->sge[0].length = head->count; /* save count of hdr pages */ + head->hdr_count = head->count; /* save count of hdr pages */ head->arg.page_base = 0; head->arg.page_len = ch_bytes; head->arg.len = rqstp->rq_arg.len + ch_bytes; head->arg.buflen = rqstp->rq_arg.buflen + ch_bytes; head->count++; - ch_sge_ary[0].start = 0; + chl_map->ch[0].start = 0; while (byte_count) { + rpl_map->sge[sge_no].iov_base = + page_address(rqstp->rq_arg.pages[page_no]) + page_off; sge_bytes = min_t(int, PAGE_SIZE-page_off, ch_bytes); - sge[sge_no].addr = - ib_dma_map_page(xprt->sc_cm_id->device, - rqstp->rq_arg.pages[page_no], - page_off, sge_bytes, - DMA_FROM_DEVICE); - sge[sge_no].length = sge_bytes; - sge[sge_no].lkey = xprt->sc_phys_mr->lkey; + rpl_map->sge[sge_no].iov_len = sge_bytes; /* * Don't bump head->count here because the same page * may be used by multiple SGE. @@ -187,11 +178,11 @@ static int rdma_rcl_to_sge(struct svcxprt_rdma *xprt, * SGE, move to the next SGE */ if (ch_bytes == 0) { - ch_sge_ary[ch_no].count = - sge_no - ch_sge_ary[ch_no].start; + chl_map->ch[ch_no].count = + sge_no - chl_map->ch[ch_no].start; ch_no++; ch++; - ch_sge_ary[ch_no].start = sge_no; + chl_map->ch[ch_no].start = sge_no; ch_bytes = ch->rc_target.rs_length; /* If bytes remaining account for next chunk */ if (byte_count) { @@ -220,18 +211,24 @@ static int rdma_rcl_to_sge(struct svcxprt_rdma *xprt, return sge_no; } -static void rdma_set_ctxt_sge(struct svc_rdma_op_ctxt *ctxt, - struct ib_sge *sge, +static void rdma_set_ctxt_sge(struct svcxprt_rdma *xprt, + struct svc_rdma_op_ctxt *ctxt, + struct kvec *vec, u64 *sgl_offset, int count) { int i; ctxt->count = count; + ctxt->direction = DMA_FROM_DEVICE; for (i = 0; i < count; i++) { - ctxt->sge[i].addr = sge[i].addr; - ctxt->sge[i].length = sge[i].length; - *sgl_offset = *sgl_offset + sge[i].length; + ctxt->sge[i].addr = + ib_dma_map_single(xprt->sc_cm_id->device, + vec[i].iov_base, vec[i].iov_len, + DMA_FROM_DEVICE); + ctxt->sge[i].length = vec[i].iov_len; + ctxt->sge[i].lkey = xprt->sc_phys_mr->lkey; + *sgl_offset = *sgl_offset + vec[i].iov_len; } } @@ -282,34 +279,29 @@ static int rdma_read_xdr(struct svcxprt_rdma *xprt, struct ib_send_wr read_wr; int err = 0; int ch_no; - struct ib_sge *sge; int ch_count; int byte_count; int sge_count; u64 sgl_offset; struct rpcrdma_read_chunk *ch; struct svc_rdma_op_ctxt *ctxt = NULL; - struct svc_rdma_op_ctxt *tmp_sge_ctxt; - struct svc_rdma_op_ctxt *tmp_ch_ctxt; - struct chunk_sge *ch_sge_ary; + struct svc_rdma_req_map *rpl_map; + struct svc_rdma_req_map *chl_map; /* If no read list is present, return 0 */ ch = svc_rdma_get_read_chunk(rmsgp); if (!ch) return 0; - /* Allocate temporary contexts to keep SGE */ - BUG_ON(sizeof(struct ib_sge) < sizeof(struct chunk_sge)); - tmp_sge_ctxt = svc_rdma_get_context(xprt); - sge = tmp_sge_ctxt->sge; - tmp_ch_ctxt = svc_rdma_get_context(xprt); - ch_sge_ary = (struct chunk_sge *)tmp_ch_ctxt->sge; + /* Allocate temporary reply and chunk maps */ + rpl_map = svc_rdma_get_req_map(); + chl_map = svc_rdma_get_req_map(); svc_rdma_rcl_chunk_counts(ch, &ch_count, &byte_count); if (ch_count > RPCSVC_MAXPAGES) return -EINVAL; sge_count = rdma_rcl_to_sge(xprt, rqstp, hdr_ctxt, rmsgp, - sge, ch_sge_ary, + rpl_map, chl_map, ch_count, byte_count); sgl_offset = 0; ch_no = 0; @@ -331,14 +323,15 @@ next_sge: read_wr.wr.rdma.remote_addr = get_unaligned(&(ch->rc_target.rs_offset)) + sgl_offset; - read_wr.sg_list = &sge[ch_sge_ary[ch_no].start]; + read_wr.sg_list = ctxt->sge; read_wr.num_sge = - rdma_read_max_sge(xprt, ch_sge_ary[ch_no].count); - rdma_set_ctxt_sge(ctxt, &sge[ch_sge_ary[ch_no].start], + rdma_read_max_sge(xprt, chl_map->ch[ch_no].count); + rdma_set_ctxt_sge(xprt, ctxt, + &rpl_map->sge[chl_map->ch[ch_no].start], &sgl_offset, read_wr.num_sge); if (((ch+1)->rc_discrim == 0) && - (read_wr.num_sge == ch_sge_ary[ch_no].count)) { + (read_wr.num_sge == chl_map->ch[ch_no].count)) { /* * Mark the last RDMA_READ with a bit to * indicate all RPC data has been fetched from @@ -358,9 +351,9 @@ next_sge: } atomic_inc(&rdma_stat_read); - if (read_wr.num_sge < ch_sge_ary[ch_no].count) { - ch_sge_ary[ch_no].count -= read_wr.num_sge; - ch_sge_ary[ch_no].start += read_wr.num_sge; + if (read_wr.num_sge < chl_map->ch[ch_no].count) { + chl_map->ch[ch_no].count -= read_wr.num_sge; + chl_map->ch[ch_no].start += read_wr.num_sge; goto next_sge; } sgl_offset = 0; @@ -368,8 +361,8 @@ next_sge: } out: - svc_rdma_put_context(tmp_sge_ctxt, 0); - svc_rdma_put_context(tmp_ch_ctxt, 0); + svc_rdma_put_req_map(rpl_map); + svc_rdma_put_req_map(chl_map); /* Detach arg pages. svc_recv will replenish them */ for (ch_no = 0; &rqstp->rq_pages[ch_no] < rqstp->rq_respages; ch_no++) @@ -399,7 +392,7 @@ static int rdma_read_complete(struct svc_rqst *rqstp, rqstp->rq_pages[page_no] = head->pages[page_no]; } /* Point rq_arg.pages past header */ - rqstp->rq_arg.pages = &rqstp->rq_pages[head->sge[0].length]; + rqstp->rq_arg.pages = &rqstp->rq_pages[head->hdr_count]; rqstp->rq_arg.page_len = head->arg.page_len; rqstp->rq_arg.page_base = head->arg.page_base; From e6ab9143719ff76f0b95f0866c4d0f6c743ad2e0 Mon Sep 17 00:00:00 2001 From: Tom Tucker Date: Wed, 28 May 2008 12:08:48 -0500 Subject: [PATCH 31/51] svcrdma: Move the DMA unmap logic to the CQ handler Separate DMA unmap from context destruction and perform DMA unmapping in the SQ/RQ CQ reap functions. This is necessary to support software based RDMA implementations that actually copy the data in their ib_dma_unmap callback functions and architectures that don't have cache coherent I/O busses. Signed-off-by: Tom Tucker --- net/sunrpc/xprtrdma/svc_rdma_transport.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index fc86338bcbb2..7e8ee66458ea 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -150,6 +150,18 @@ struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) return ctxt; } +static void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt) +{ + struct svcxprt_rdma *xprt = ctxt->xprt; + int i; + for (i = 0; i < ctxt->count && ctxt->sge[i].length; i++) { + ib_dma_unmap_single(xprt->sc_cm_id->device, + ctxt->sge[i].addr, + ctxt->sge[i].length, + ctxt->direction); + } +} + void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages) { struct svcxprt_rdma *xprt; @@ -161,12 +173,6 @@ void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages) for (i = 0; i < ctxt->count; i++) put_page(ctxt->pages[i]); - for (i = 0; i < ctxt->count; i++) - ib_dma_unmap_single(xprt->sc_cm_id->device, - ctxt->sge[i].addr, - ctxt->sge[i].length, - ctxt->direction); - spin_lock_bh(&xprt->sc_ctxt_lock); list_add(&ctxt->free_list, &xprt->sc_ctxt_free); spin_unlock_bh(&xprt->sc_ctxt_lock); @@ -328,6 +334,7 @@ static void rq_cq_reap(struct svcxprt_rdma *xprt) ctxt = (struct svc_rdma_op_ctxt *)(unsigned long)wc.wr_id; ctxt->wc_status = wc.status; ctxt->byte_len = wc.byte_len; + svc_rdma_unmap_dma(ctxt); if (wc.status != IB_WC_SUCCESS) { /* Close the transport */ dprintk("svcrdma: transport closing putting ctxt %p\n", ctxt); @@ -377,6 +384,7 @@ static void sq_cq_reap(struct svcxprt_rdma *xprt) ctxt = (struct svc_rdma_op_ctxt *)(unsigned long)wc.wr_id; xprt = ctxt->xprt; + svc_rdma_unmap_dma(ctxt); if (wc.status != IB_WC_SUCCESS) /* Close the transport */ set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); From 87295b6c5c7fd7bbc0ce3e7f42d2adbbac7352b9 Mon Sep 17 00:00:00 2001 From: Tom Tucker Date: Wed, 28 May 2008 13:17:44 -0500 Subject: [PATCH 32/51] svcrdma: Add dma map count and WARN_ON Add a dma map count in order to verify that all DMA mapping resources have been freed when the transport is closed. Signed-off-by: Tom Tucker --- include/linux/sunrpc/svc_rdma.h | 1 + net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 1 + net/sunrpc/xprtrdma/svc_rdma_sendto.c | 3 +++ net/sunrpc/xprtrdma/svc_rdma_transport.c | 5 +++++ 4 files changed, 10 insertions(+) diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index fd5e8a1c17de..ab93afc03c43 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -130,6 +130,7 @@ struct svcxprt_rdma { struct ib_pd *sc_pd; + atomic_t sc_dma_used; atomic_t sc_ctxt_used; struct list_head sc_ctxt_free; int sc_ctxt_cnt; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index d25971b42a74..b4b17f44cb29 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -222,6 +222,7 @@ static void rdma_set_ctxt_sge(struct svcxprt_rdma *xprt, ctxt->count = count; ctxt->direction = DMA_FROM_DEVICE; for (i = 0; i < count; i++) { + atomic_inc(&xprt->sc_dma_used); ctxt->sge[i].addr = ib_dma_map_single(xprt->sc_cm_id->device, vec[i].iov_base, vec[i].iov_len, diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index bdc11a30e937..a19b22b452a3 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -163,6 +163,7 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, sge_bytes = min((size_t)bc, (size_t)(vec->sge[xdr_sge_no].iov_len-sge_off)); sge[sge_no].length = sge_bytes; + atomic_inc(&xprt->sc_dma_used); sge[sge_no].addr = ib_dma_map_single(xprt->sc_cm_id->device, (void *) @@ -385,6 +386,7 @@ static int send_reply(struct svcxprt_rdma *rdma, ctxt->count = 1; /* Prepare the SGE for the RPCRDMA Header */ + atomic_inc(&rdma->sc_dma_used); ctxt->sge[0].addr = ib_dma_map_page(rdma->sc_cm_id->device, page, 0, PAGE_SIZE, DMA_TO_DEVICE); @@ -396,6 +398,7 @@ static int send_reply(struct svcxprt_rdma *rdma, for (sge_no = 1; byte_count && sge_no < vec->count; sge_no++) { sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count); byte_count -= sge_bytes; + atomic_inc(&rdma->sc_dma_used); ctxt->sge[sge_no].addr = ib_dma_map_single(rdma->sc_cm_id->device, vec->sge[sge_no].iov_base, diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 7e8ee66458ea..6fddd588c031 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -155,6 +155,7 @@ static void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt) struct svcxprt_rdma *xprt = ctxt->xprt; int i; for (i = 0; i < ctxt->count && ctxt->sge[i].length; i++) { + atomic_dec(&xprt->sc_dma_used); ib_dma_unmap_single(xprt->sc_cm_id->device, ctxt->sge[i].addr, ctxt->sge[i].length, @@ -519,6 +520,7 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, cma_xprt->sc_max_requests = svcrdma_max_requests; cma_xprt->sc_sq_depth = svcrdma_max_requests * RPCRDMA_SQ_DEPTH_MULT; atomic_set(&cma_xprt->sc_sq_count, 0); + atomic_set(&cma_xprt->sc_ctxt_used, 0); if (!listener) { int reqs = cma_xprt->sc_max_requests; @@ -569,6 +571,7 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt) BUG_ON(sge_no >= xprt->sc_max_sge); page = svc_rdma_get_page(); ctxt->pages[sge_no] = page; + atomic_inc(&xprt->sc_dma_used); pa = ib_dma_map_page(xprt->sc_cm_id->device, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); @@ -1049,6 +1052,7 @@ static void __svc_rdma_free(struct work_struct *work) /* Warn if we leaked a resource or under-referenced */ WARN_ON(atomic_read(&rdma->sc_ctxt_used) != 0); + WARN_ON(atomic_read(&rdma->sc_dma_used) != 0); /* Destroy the QP if present (not a listener) */ if (rdma->sc_qp && !IS_ERR(rdma->sc_qp)) @@ -1169,6 +1173,7 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, length = svc_rdma_xdr_encode_error(xprt, rmsgp, err, va); /* Prepare SGE for local address */ + atomic_inc(&xprt->sc_dma_used); sge.addr = ib_dma_map_page(xprt->sc_cm_id->device, p, 0, PAGE_SIZE, DMA_FROM_DEVICE); sge.lkey = xprt->sc_phys_mr->lkey; From 94dba4918d4570bfa98776e54a5fa527c848dc78 Mon Sep 17 00:00:00 2001 From: Tom Tucker Date: Wed, 28 May 2008 13:20:24 -0500 Subject: [PATCH 33/51] svcrdma: Remove unneeded spin locks from __svc_rdma_free At the time __svc_rdma_free is called, we are guaranteed that all references to this transport are gone. There is, therefore, no need to protect the resource lists with a spin lock. Signed-off-by: Tom Tucker --- net/sunrpc/xprtrdma/svc_rdma_transport.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 6fddd588c031..7647789a1f68 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -1027,7 +1027,6 @@ static void __svc_rdma_free(struct work_struct *work) * cm_id because the device ptr is needed to unmap the dma in * svc_rdma_put_context. */ - spin_lock_bh(&rdma->sc_read_complete_lock); while (!list_empty(&rdma->sc_read_complete_q)) { struct svc_rdma_op_ctxt *ctxt; ctxt = list_entry(rdma->sc_read_complete_q.next, @@ -1036,10 +1035,8 @@ static void __svc_rdma_free(struct work_struct *work) list_del_init(&ctxt->dto_q); svc_rdma_put_context(ctxt, 1); } - spin_unlock_bh(&rdma->sc_read_complete_lock); /* Destroy queued, but not processed recv completions */ - spin_lock_bh(&rdma->sc_rq_dto_lock); while (!list_empty(&rdma->sc_rq_dto_q)) { struct svc_rdma_op_ctxt *ctxt; ctxt = list_entry(rdma->sc_rq_dto_q.next, @@ -1048,7 +1045,6 @@ static void __svc_rdma_free(struct work_struct *work) list_del_init(&ctxt->dto_q); svc_rdma_put_context(ctxt, 1); } - spin_unlock_bh(&rdma->sc_rq_dto_lock); /* Warn if we leaked a resource or under-referenced */ WARN_ON(atomic_read(&rdma->sc_ctxt_used) != 0); From 779a48577ba88b6a7e9748a04b0b739f36c5e6f6 Mon Sep 17 00:00:00 2001 From: Tom Tucker Date: Mon, 19 May 2008 10:17:09 -0500 Subject: [PATCH 34/51] svcrdma: Remove unused wait q from svcrdma_xprt structure The sc_read_wait queue head is no longer used. Remove it. Signed-off-by: Tom Tucker --- include/linux/sunrpc/svc_rdma.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index ab93afc03c43..d8d74c4ab504 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -119,7 +119,6 @@ struct svcxprt_rdma { struct rdma_cm_id *sc_cm_id; /* RDMA connection id */ struct list_head sc_accept_q; /* Conn. waiting accept */ int sc_ord; /* RDMA read limit */ - wait_queue_head_t sc_read_wait; int sc_max_sge; int sc_sq_depth; /* Depth of SQ */ From 36ef25e464dbc5820c22a9b2f619b787eda594df Mon Sep 17 00:00:00 2001 From: Tom Tucker Date: Mon, 19 May 2008 19:00:24 -0500 Subject: [PATCH 35/51] svcrdma: Limit ORD based on client's advertised IRD When adapters have differing IRD limits, the RDMA transport will fail to connect properly. The RDMA transport should use the client's advertised inbound read limit when computing its outbound read limit. For iWARP transports, there is currently no standard for exchanging IRD/ORD during connection establishment so the 'responder_resources' field in the connect event is the local device's limit. The RDMA transport can be configured to use a smaller ORD by writing the desired number to the /proc/sys/sunrpc/svc_rdma/max_outbound_read_requests file. Signed-off-by: Tom Tucker --- net/sunrpc/xprtrdma/svc_rdma_transport.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 7647789a1f68..80104f4999d5 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -606,7 +606,7 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt) * will call the recvfrom method on the listen xprt which will accept the new * connection. */ -static void handle_connect_req(struct rdma_cm_id *new_cma_id) +static void handle_connect_req(struct rdma_cm_id *new_cma_id, size_t client_ird) { struct svcxprt_rdma *listen_xprt = new_cma_id->context; struct svcxprt_rdma *newxprt; @@ -623,6 +623,9 @@ static void handle_connect_req(struct rdma_cm_id *new_cma_id) dprintk("svcrdma: Creating newxprt=%p, cm_id=%p, listenxprt=%p\n", newxprt, newxprt->sc_cm_id, listen_xprt); + /* Save client advertised inbound read limit for use later in accept. */ + newxprt->sc_ord = client_ird; + /* Set the local and remote addresses in the transport */ sa = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.dst_addr; svc_xprt_set_remote(&newxprt->sc_xprt, sa, svc_addr_len(sa)); @@ -659,7 +662,8 @@ static int rdma_listen_handler(struct rdma_cm_id *cma_id, case RDMA_CM_EVENT_CONNECT_REQUEST: dprintk("svcrdma: Connect request on cma_id=%p, xprt = %p, " "event=%d\n", cma_id, cma_id->context, event->event); - handle_connect_req(cma_id); + handle_connect_req(cma_id, + event->param.conn.responder_resources); break; case RDMA_CM_EVENT_ESTABLISHED: @@ -833,8 +837,12 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) (size_t)svcrdma_max_requests); newxprt->sc_sq_depth = RPCRDMA_SQ_DEPTH_MULT * newxprt->sc_max_requests; - newxprt->sc_ord = min((size_t)devattr.max_qp_rd_atom, - (size_t)svcrdma_ord); + /* + * Limit ORD based on client limit, local device limit, and + * configured svcrdma limit. + */ + newxprt->sc_ord = min_t(size_t, devattr.max_qp_rd_atom, newxprt->sc_ord); + newxprt->sc_ord = min_t(size_t, svcrdma_ord, newxprt->sc_ord); newxprt->sc_pd = ib_alloc_pd(newxprt->sc_cm_id->device); if (IS_ERR(newxprt->sc_pd)) { From 902a94e0889be1f9fcefc0e1b602b06136e01812 Mon Sep 17 00:00:00 2001 From: Tom Tucker Date: Wed, 28 May 2008 13:57:05 -0500 Subject: [PATCH 36/51] svcrdma: Add flush_scheduled_work to module exit function Make certain all transports pending free are flushed from the wq before unloading the module. Signed-off-by: Tom Tucker --- net/sunrpc/xprtrdma/svc_rdma.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 171f2053e90c..527acfd38284 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -239,6 +239,7 @@ static ctl_table svcrdma_root_table[] = { void svc_rdma_cleanup(void) { dprintk("SVCRDMA Module Removed, deregister RPC RDMA transport\n"); + flush_scheduled_work(); if (svcrdma_table_header) { unregister_sysctl_table(svcrdma_table_header); svcrdma_table_header = NULL; From bf5927d84e70d522f234ca247b27d27c63878b93 Mon Sep 17 00:00:00 2001 From: Tom Tucker Date: Wed, 28 May 2008 14:05:54 -0500 Subject: [PATCH 37/51] svcrdma: Create a kmem cache for the WR contexts Create a kmem cache to hold WR contexts. Next we will convert the WR context get and put services to use this kmem cache. Signed-off-by: Tom Tucker --- net/sunrpc/xprtrdma/svc_rdma.c | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 527acfd38284..87101177825b 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -69,8 +69,9 @@ atomic_t rdma_stat_rq_prod; atomic_t rdma_stat_sq_poll; atomic_t rdma_stat_sq_prod; -/* Temporary NFS request map cache */ +/* Temporary NFS request map and context caches */ struct kmem_cache *svc_rdma_map_cachep; +struct kmem_cache *svc_rdma_ctxt_cachep; /* * This function implements reading and resetting an atomic_t stat @@ -246,6 +247,7 @@ void svc_rdma_cleanup(void) } svc_unreg_xprt_class(&svc_rdma_class); kmem_cache_destroy(svc_rdma_map_cachep); + kmem_cache_destroy(svc_rdma_ctxt_cachep); } int svc_rdma_init(void) @@ -268,14 +270,27 @@ int svc_rdma_init(void) NULL); if (!svc_rdma_map_cachep) { printk(KERN_INFO "Could not allocate map cache.\n"); - goto err; + goto err0; + } + + /* Create the temporary context cache */ + svc_rdma_ctxt_cachep = + kmem_cache_create("svc_rdma_ctxt_cache", + sizeof(struct svc_rdma_op_ctxt), + 0, + SLAB_HWCACHE_ALIGN, + NULL); + if (!svc_rdma_ctxt_cachep) { + printk(KERN_INFO "Could not allocate WR ctxt cache.\n"); + goto err1; } /* Register RDMA with the SVC transport switch */ svc_reg_xprt_class(&svc_rdma_class); return 0; - - err: + err1: + kmem_cache_destroy(svc_rdma_map_cachep); + err0: unregister_sysctl_table(svcrdma_table_header); return -ENOMEM; } From 8948896c9e098c6fd31a6a698a598a7cbd7fa40e Mon Sep 17 00:00:00 2001 From: Tom Tucker Date: Wed, 28 May 2008 15:14:02 -0500 Subject: [PATCH 38/51] svcrdma: Change WR context get/put to use the kmem cache Change the WR context pool to be shared across mount points. This reduces the RDMA transport memory footprint significantly since idle mounts don't consume WR context memory. Signed-off-by: Tom Tucker --- include/linux/sunrpc/svc_rdma.h | 6 -- net/sunrpc/xprtrdma/svc_rdma_transport.c | 121 +++-------------------- 2 files changed, 12 insertions(+), 115 deletions(-) diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index d8d74c4ab504..ef2e3a20bf3b 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -73,7 +73,6 @@ extern atomic_t rdma_stat_sq_prod; struct svc_rdma_op_ctxt { struct svc_rdma_op_ctxt *read_hdr; int hdr_count; - struct list_head free_list; struct xdr_buf arg; struct list_head dto_q; enum ib_wr_opcode wr_op; @@ -131,11 +130,6 @@ struct svcxprt_rdma { atomic_t sc_dma_used; atomic_t sc_ctxt_used; - struct list_head sc_ctxt_free; - int sc_ctxt_cnt; - int sc_ctxt_bump; - int sc_ctxt_max; - spinlock_t sc_ctxt_lock; struct list_head sc_rq_dto_q; spinlock_t sc_rq_dto_lock; struct ib_qp *sc_qp; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 80104f4999d5..19ddc382b777 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -84,69 +84,23 @@ struct svc_xprt_class svc_rdma_class = { .xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP, }; -static int rdma_bump_context_cache(struct svcxprt_rdma *xprt) -{ - int target; - int at_least_one = 0; - struct svc_rdma_op_ctxt *ctxt; - - target = min(xprt->sc_ctxt_cnt + xprt->sc_ctxt_bump, - xprt->sc_ctxt_max); - - spin_lock_bh(&xprt->sc_ctxt_lock); - while (xprt->sc_ctxt_cnt < target) { - xprt->sc_ctxt_cnt++; - spin_unlock_bh(&xprt->sc_ctxt_lock); - - ctxt = kmalloc(sizeof(*ctxt), GFP_KERNEL); - - spin_lock_bh(&xprt->sc_ctxt_lock); - if (ctxt) { - at_least_one = 1; - INIT_LIST_HEAD(&ctxt->free_list); - list_add(&ctxt->free_list, &xprt->sc_ctxt_free); - } else { - /* kmalloc failed...give up for now */ - xprt->sc_ctxt_cnt--; - break; - } - } - spin_unlock_bh(&xprt->sc_ctxt_lock); - dprintk("svcrdma: sc_ctxt_max=%d, sc_ctxt_cnt=%d\n", - xprt->sc_ctxt_max, xprt->sc_ctxt_cnt); - return at_least_one; -} +/* WR context cache. Created in svc_rdma.c */ +extern struct kmem_cache *svc_rdma_ctxt_cachep; struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) { struct svc_rdma_op_ctxt *ctxt; while (1) { - spin_lock_bh(&xprt->sc_ctxt_lock); - if (unlikely(list_empty(&xprt->sc_ctxt_free))) { - /* Try to bump my cache. */ - spin_unlock_bh(&xprt->sc_ctxt_lock); - - if (rdma_bump_context_cache(xprt)) - continue; - - printk(KERN_INFO "svcrdma: sleeping waiting for " - "context memory on xprt=%p\n", - xprt); - schedule_timeout_uninterruptible(msecs_to_jiffies(500)); - continue; - } - ctxt = list_entry(xprt->sc_ctxt_free.next, - struct svc_rdma_op_ctxt, - free_list); - list_del_init(&ctxt->free_list); - spin_unlock_bh(&xprt->sc_ctxt_lock); - ctxt->xprt = xprt; - INIT_LIST_HEAD(&ctxt->dto_q); - ctxt->count = 0; - atomic_inc(&xprt->sc_ctxt_used); - break; + ctxt = kmem_cache_alloc(svc_rdma_ctxt_cachep, GFP_KERNEL); + if (ctxt) + break; + schedule_timeout_uninterruptible(msecs_to_jiffies(500)); } + ctxt->xprt = xprt; + INIT_LIST_HEAD(&ctxt->dto_q); + ctxt->count = 0; + atomic_inc(&xprt->sc_ctxt_used); return ctxt; } @@ -174,9 +128,7 @@ void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages) for (i = 0; i < ctxt->count; i++) put_page(ctxt->pages[i]); - spin_lock_bh(&xprt->sc_ctxt_lock); - list_add(&ctxt->free_list, &xprt->sc_ctxt_free); - spin_unlock_bh(&xprt->sc_ctxt_lock); + kmem_cache_free(svc_rdma_ctxt_cachep, ctxt); atomic_dec(&xprt->sc_ctxt_used); } @@ -461,40 +413,6 @@ static void sq_comp_handler(struct ib_cq *cq, void *cq_context) tasklet_schedule(&dto_tasklet); } -static void create_context_cache(struct svcxprt_rdma *xprt, - int ctxt_count, int ctxt_bump, int ctxt_max) -{ - struct svc_rdma_op_ctxt *ctxt; - int i; - - xprt->sc_ctxt_max = ctxt_max; - xprt->sc_ctxt_bump = ctxt_bump; - xprt->sc_ctxt_cnt = 0; - atomic_set(&xprt->sc_ctxt_used, 0); - - INIT_LIST_HEAD(&xprt->sc_ctxt_free); - for (i = 0; i < ctxt_count; i++) { - ctxt = kmalloc(sizeof(*ctxt), GFP_KERNEL); - if (ctxt) { - INIT_LIST_HEAD(&ctxt->free_list); - list_add(&ctxt->free_list, &xprt->sc_ctxt_free); - xprt->sc_ctxt_cnt++; - } - } -} - -static void destroy_context_cache(struct svcxprt_rdma *xprt) -{ - while (!list_empty(&xprt->sc_ctxt_free)) { - struct svc_rdma_op_ctxt *ctxt; - ctxt = list_entry(xprt->sc_ctxt_free.next, - struct svc_rdma_op_ctxt, - free_list); - list_del_init(&ctxt->free_list); - kfree(ctxt); - } -} - static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, int listener) { @@ -511,7 +429,6 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, spin_lock_init(&cma_xprt->sc_lock); spin_lock_init(&cma_xprt->sc_read_complete_lock); - spin_lock_init(&cma_xprt->sc_ctxt_lock); spin_lock_init(&cma_xprt->sc_rq_dto_lock); cma_xprt->sc_ord = svcrdma_ord; @@ -522,20 +439,7 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, atomic_set(&cma_xprt->sc_sq_count, 0); atomic_set(&cma_xprt->sc_ctxt_used, 0); - if (!listener) { - int reqs = cma_xprt->sc_max_requests; - create_context_cache(cma_xprt, - reqs << 1, /* starting size */ - reqs, /* bump amount */ - reqs + - cma_xprt->sc_sq_depth + - RPCRDMA_MAX_THREADS + 1); /* max */ - if (list_empty(&cma_xprt->sc_ctxt_free)) { - kfree(cma_xprt); - return NULL; - } - clear_bit(XPT_LISTENER, &cma_xprt->sc_xprt.xpt_flags); - } else + if (listener) set_bit(XPT_LISTENER, &cma_xprt->sc_xprt.xpt_flags); return cma_xprt; @@ -1077,7 +981,6 @@ static void __svc_rdma_free(struct work_struct *work) /* Destroy the CM ID */ rdma_destroy_id(rdma->sc_cm_id); - destroy_context_cache(rdma); kfree(rdma); } From b001a1b6aa960949a24c2cdc28257dfcc9428d74 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Wed, 2 Jul 2008 11:15:03 +0300 Subject: [PATCH 39/51] nfsd: dprint operation names Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 52 ++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 50 insertions(+), 2 deletions(-) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 5c3683cfd59e..eef1629806f5 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -846,10 +846,13 @@ struct nfsd4_operation { #define ALLOWED_WITHOUT_FH 1 /* GETATTR and ops not listed as returning NFS4ERR_MOVED: */ #define ALLOWED_ON_ABSENT_FS 2 + char *op_name; }; static struct nfsd4_operation nfsd4_ops[]; +static inline char *nfsd4_op_name(unsigned opnum); + /* * COMPOUND call. */ @@ -891,7 +894,9 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, while (!status && resp->opcnt < args->opcnt) { op = &args->ops[resp->opcnt++]; - dprintk("nfsv4 compound op #%d: %d\n", resp->opcnt, op->opnum); + dprintk("nfsv4 compound op #%d/%d: %d (%s)\n", + resp->opcnt, args->opcnt, op->opnum, + nfsd4_op_name(op->opnum)); /* * The XDR decode routines may have pre-set op->status; @@ -962,120 +967,163 @@ out: static struct nfsd4_operation nfsd4_ops[OP_RELEASE_LOCKOWNER+1] = { [OP_ACCESS] = { .op_func = (nfsd4op_func)nfsd4_access, + .op_name = "OP_ACCESS", }, [OP_CLOSE] = { .op_func = (nfsd4op_func)nfsd4_close, + .op_name = "OP_CLOSE", }, [OP_COMMIT] = { .op_func = (nfsd4op_func)nfsd4_commit, + .op_name = "OP_COMMIT", }, [OP_CREATE] = { .op_func = (nfsd4op_func)nfsd4_create, + .op_name = "OP_CREATE", }, [OP_DELEGRETURN] = { .op_func = (nfsd4op_func)nfsd4_delegreturn, + .op_name = "OP_DELEGRETURN", }, [OP_GETATTR] = { .op_func = (nfsd4op_func)nfsd4_getattr, .op_flags = ALLOWED_ON_ABSENT_FS, + .op_name = "OP_GETATTR", }, [OP_GETFH] = { .op_func = (nfsd4op_func)nfsd4_getfh, + .op_name = "OP_GETFH", }, [OP_LINK] = { .op_func = (nfsd4op_func)nfsd4_link, + .op_name = "OP_LINK", }, [OP_LOCK] = { .op_func = (nfsd4op_func)nfsd4_lock, + .op_name = "OP_LOCK", }, [OP_LOCKT] = { .op_func = (nfsd4op_func)nfsd4_lockt, + .op_name = "OP_LOCKT", }, [OP_LOCKU] = { .op_func = (nfsd4op_func)nfsd4_locku, + .op_name = "OP_LOCKU", }, [OP_LOOKUP] = { .op_func = (nfsd4op_func)nfsd4_lookup, + .op_name = "OP_LOOKUP", }, [OP_LOOKUPP] = { .op_func = (nfsd4op_func)nfsd4_lookupp, + .op_name = "OP_LOOKUPP", }, [OP_NVERIFY] = { .op_func = (nfsd4op_func)nfsd4_nverify, + .op_name = "OP_NVERIFY", }, [OP_OPEN] = { .op_func = (nfsd4op_func)nfsd4_open, + .op_name = "OP_OPEN", }, [OP_OPEN_CONFIRM] = { .op_func = (nfsd4op_func)nfsd4_open_confirm, + .op_name = "OP_OPEN_CONFIRM", }, [OP_OPEN_DOWNGRADE] = { .op_func = (nfsd4op_func)nfsd4_open_downgrade, + .op_name = "OP_OPEN_DOWNGRADE", }, [OP_PUTFH] = { .op_func = (nfsd4op_func)nfsd4_putfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS, + .op_name = "OP_PUTFH", }, [OP_PUTPUBFH] = { - /* unsupported; just for future reference: */ + /* unsupported, just for future reference: */ .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS, + .op_name = "OP_PUTPUBFH", }, [OP_PUTROOTFH] = { .op_func = (nfsd4op_func)nfsd4_putrootfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS, + .op_name = "OP_PUTROOTFH", }, [OP_READ] = { .op_func = (nfsd4op_func)nfsd4_read, + .op_name = "OP_READ", }, [OP_READDIR] = { .op_func = (nfsd4op_func)nfsd4_readdir, + .op_name = "OP_READDIR", }, [OP_READLINK] = { .op_func = (nfsd4op_func)nfsd4_readlink, + .op_name = "OP_READLINK", }, [OP_REMOVE] = { .op_func = (nfsd4op_func)nfsd4_remove, + .op_name = "OP_REMOVE", }, [OP_RENAME] = { + .op_name = "OP_RENAME", .op_func = (nfsd4op_func)nfsd4_rename, }, [OP_RENEW] = { .op_func = (nfsd4op_func)nfsd4_renew, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS, + .op_name = "OP_RENEW", }, [OP_RESTOREFH] = { .op_func = (nfsd4op_func)nfsd4_restorefh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS, + .op_name = "OP_RESTOREFH", }, [OP_SAVEFH] = { .op_func = (nfsd4op_func)nfsd4_savefh, + .op_name = "OP_SAVEFH", }, [OP_SECINFO] = { .op_func = (nfsd4op_func)nfsd4_secinfo, + .op_name = "OP_SECINFO", }, [OP_SETATTR] = { .op_func = (nfsd4op_func)nfsd4_setattr, + .op_name = "OP_SETATTR", }, [OP_SETCLIENTID] = { .op_func = (nfsd4op_func)nfsd4_setclientid, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS, + .op_name = "OP_SETCLIENTID", }, [OP_SETCLIENTID_CONFIRM] = { .op_func = (nfsd4op_func)nfsd4_setclientid_confirm, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS, + .op_name = "OP_SETCLIENTID_CONFIRM", }, [OP_VERIFY] = { .op_func = (nfsd4op_func)nfsd4_verify, + .op_name = "OP_VERIFY", }, [OP_WRITE] = { .op_func = (nfsd4op_func)nfsd4_write, + .op_name = "OP_WRITE", }, [OP_RELEASE_LOCKOWNER] = { .op_func = (nfsd4op_func)nfsd4_release_lockowner, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS, + .op_name = "OP_RELEASE_LOCKOWNER", }, }; +static inline char * +nfsd4_op_name(unsigned opnum) +{ + if (opnum < ARRAY_SIZE(nfsd4_ops)) + return nfsd4_ops[opnum].op_name; + return "unknown_operation"; +} + #define nfs4svc_decode_voidargs NULL #define nfs4svc_release_void NULL #define nfsd4_voidres nfsd4_voidargs From 695e12f8d2917378d3b93059209e17415de96204 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 4 Jul 2008 14:38:33 +0300 Subject: [PATCH 40/51] nfsd: tabulate nfs4 xdr encoding functions In preparation for minorversion 1 All encoders now return an nfserr status (typically their nfserr argument). Unsupported ops go through nfsd4_encode_operation too, so use nfsd4_encode_noop to encode nothing for their reply body. Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 205 ++++++++++++++++++++-------------------------- 1 file changed, 91 insertions(+), 114 deletions(-) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index a40bec53fa66..9b6a9bafc6b4 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1950,7 +1950,7 @@ fail: return -EINVAL; } -static void +static __be32 nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_access *access) { ENCODE_HEAD; @@ -1961,9 +1961,10 @@ nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ WRITE32(access->ac_resp_access); ADJUST_ARGS(); } + return nfserr; } -static void +static __be32 nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close) { ENCODE_SEQID_OP_HEAD; @@ -1975,10 +1976,11 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_c ADJUST_ARGS(); } ENCODE_SEQID_OP_TAIL(close->cl_stateowner); + return nfserr; } -static void +static __be32 nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_commit *commit) { ENCODE_HEAD; @@ -1988,9 +1990,10 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ WRITEMEM(commit->co_verf.data, 8); ADJUST_ARGS(); } + return nfserr; } -static void +static __be32 nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create *create) { ENCODE_HEAD; @@ -2003,6 +2006,7 @@ nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ WRITE32(create->cr_bmval[1]); ADJUST_ARGS(); } + return nfserr; } static __be32 @@ -2023,9 +2027,10 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 return nfserr; } -static void -nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh *fhp) +static __be32 +nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh **fhpp) { + struct svc_fh *fhp = *fhpp; unsigned int len; ENCODE_HEAD; @@ -2036,6 +2041,7 @@ nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh WRITEMEM(&fhp->fh_handle.fh_base, len); ADJUST_ARGS(); } + return nfserr; } /* @@ -2063,7 +2069,7 @@ nfsd4_encode_lock_denied(struct nfsd4_compoundres *resp, struct nfsd4_lock_denie ADJUST_ARGS(); } -static void +static __be32 nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lock *lock) { ENCODE_SEQID_OP_HEAD; @@ -2077,16 +2083,18 @@ nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lo nfsd4_encode_lock_denied(resp, &lock->lk_denied); ENCODE_SEQID_OP_TAIL(lock->lk_replay_owner); + return nfserr; } -static void +static __be32 nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lockt *lockt) { if (nfserr == nfserr_denied) nfsd4_encode_lock_denied(resp, &lockt->lt_denied); + return nfserr; } -static void +static __be32 nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_locku *locku) { ENCODE_SEQID_OP_HEAD; @@ -2099,10 +2107,11 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l } ENCODE_SEQID_OP_TAIL(locku->lu_stateowner); + return nfserr; } -static void +static __be32 nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_link *link) { ENCODE_HEAD; @@ -2112,10 +2121,11 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_li WRITECINFO(link->li_cinfo); ADJUST_ARGS(); } + return nfserr; } -static void +static __be32 nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open) { ENCODE_SEQID_OP_HEAD; @@ -2178,9 +2188,10 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op /* XXX save filehandle here */ out: ENCODE_SEQID_OP_TAIL(open->op_stateowner); + return nfserr; } -static void +static __be32 nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc) { ENCODE_SEQID_OP_HEAD; @@ -2193,9 +2204,10 @@ nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct } ENCODE_SEQID_OP_TAIL(oc->oc_stateowner); + return nfserr; } -static void +static __be32 nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od) { ENCODE_SEQID_OP_HEAD; @@ -2208,6 +2220,7 @@ nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struc } ENCODE_SEQID_OP_TAIL(od->od_stateowner); + return nfserr; } static __be32 @@ -2402,7 +2415,7 @@ err_no_verf: return nfserr; } -static void +static __be32 nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_remove *remove) { ENCODE_HEAD; @@ -2412,9 +2425,10 @@ nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ WRITECINFO(remove->rm_cinfo); ADJUST_ARGS(); } + return nfserr; } -static void +static __be32 nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_rename *rename) { ENCODE_HEAD; @@ -2425,9 +2439,10 @@ nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ WRITECINFO(rename->rn_tinfo); ADJUST_ARGS(); } + return nfserr; } -static void +static __be32 nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_secinfo *secinfo) { @@ -2491,13 +2506,14 @@ nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, out: if (exp) exp_put(exp); + return nfserr; } /* * The SETATTR encode routine is special -- it always encodes a bitmap, * regardless of the error status. */ -static void +static __be32 nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setattr *setattr) { ENCODE_HEAD; @@ -2514,9 +2530,10 @@ nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 WRITE32(setattr->sa_bmval[1]); } ADJUST_ARGS(); + return nfserr; } -static void +static __be32 nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setclientid *scd) { ENCODE_HEAD; @@ -2533,9 +2550,10 @@ nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct n WRITE32(0); ADJUST_ARGS(); } + return nfserr; } -static void +static __be32 nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_write *write) { ENCODE_HEAD; @@ -2547,8 +2565,56 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_w WRITEMEM(write->wr_verifier.data, 8); ADJUST_ARGS(); } + return nfserr; } +static __be32 +nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p) +{ + return nfserr; +} + +typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *); + +static nfsd4_enc nfsd4_enc_ops[] = { + [OP_ACCESS] (nfsd4_enc)nfsd4_encode_access, + [OP_CLOSE] (nfsd4_enc)nfsd4_encode_close, + [OP_COMMIT] (nfsd4_enc)nfsd4_encode_commit, + [OP_CREATE] (nfsd4_enc)nfsd4_encode_create, + [OP_DELEGPURGE] (nfsd4_enc)nfsd4_encode_noop, + [OP_DELEGRETURN] (nfsd4_enc)nfsd4_encode_noop, + [OP_GETATTR] (nfsd4_enc)nfsd4_encode_getattr, + [OP_GETFH] (nfsd4_enc)nfsd4_encode_getfh, + [OP_LINK] (nfsd4_enc)nfsd4_encode_link, + [OP_LOCK] (nfsd4_enc)nfsd4_encode_lock, + [OP_LOCKT] (nfsd4_enc)nfsd4_encode_lockt, + [OP_LOCKU] (nfsd4_enc)nfsd4_encode_locku, + [OP_LOOKUP] (nfsd4_enc)nfsd4_encode_noop, + [OP_LOOKUPP] (nfsd4_enc)nfsd4_encode_noop, + [OP_NVERIFY] (nfsd4_enc)nfsd4_encode_noop, + [OP_OPEN] (nfsd4_enc)nfsd4_encode_open, + [OP_OPEN_CONFIRM] (nfsd4_enc)nfsd4_encode_open_confirm, + [OP_OPEN_DOWNGRADE] (nfsd4_enc)nfsd4_encode_open_downgrade, + [OP_PUTFH] (nfsd4_enc)nfsd4_encode_noop, + [OP_PUTPUBFH] (nfsd4_enc)nfsd4_encode_noop, + [OP_PUTROOTFH] (nfsd4_enc)nfsd4_encode_noop, + [OP_READ] (nfsd4_enc)nfsd4_encode_read, + [OP_READDIR] (nfsd4_enc)nfsd4_encode_readdir, + [OP_READLINK] (nfsd4_enc)nfsd4_encode_readlink, + [OP_REMOVE] (nfsd4_enc)nfsd4_encode_remove, + [OP_RENAME] (nfsd4_enc)nfsd4_encode_rename, + [OP_RENEW] (nfsd4_enc)nfsd4_encode_noop, + [OP_RESTOREFH] (nfsd4_enc)nfsd4_encode_noop, + [OP_SAVEFH] (nfsd4_enc)nfsd4_encode_noop, + [OP_SECINFO] (nfsd4_enc)nfsd4_encode_secinfo, + [OP_SETATTR] (nfsd4_enc)nfsd4_encode_setattr, + [OP_SETCLIENTID] (nfsd4_enc)nfsd4_encode_setclientid, + [OP_SETCLIENTID_CONFIRM](nfsd4_enc)nfsd4_encode_noop, + [OP_VERIFY] (nfsd4_enc)nfsd4_encode_noop, + [OP_WRITE] (nfsd4_enc)nfsd4_encode_write, + [OP_RELEASE_LOCKOWNER] (nfsd4_enc)nfsd4_encode_noop, +}; + void nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) { @@ -2560,101 +2626,12 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) statp = p++; /* to be backfilled at the end */ ADJUST_ARGS(); - switch (op->opnum) { - case OP_ACCESS: - nfsd4_encode_access(resp, op->status, &op->u.access); - break; - case OP_CLOSE: - nfsd4_encode_close(resp, op->status, &op->u.close); - break; - case OP_COMMIT: - nfsd4_encode_commit(resp, op->status, &op->u.commit); - break; - case OP_CREATE: - nfsd4_encode_create(resp, op->status, &op->u.create); - break; - case OP_DELEGRETURN: - break; - case OP_GETATTR: - op->status = nfsd4_encode_getattr(resp, op->status, &op->u.getattr); - break; - case OP_GETFH: - nfsd4_encode_getfh(resp, op->status, op->u.getfh); - break; - case OP_LINK: - nfsd4_encode_link(resp, op->status, &op->u.link); - break; - case OP_LOCK: - nfsd4_encode_lock(resp, op->status, &op->u.lock); - break; - case OP_LOCKT: - nfsd4_encode_lockt(resp, op->status, &op->u.lockt); - break; - case OP_LOCKU: - nfsd4_encode_locku(resp, op->status, &op->u.locku); - break; - case OP_LOOKUP: - break; - case OP_LOOKUPP: - break; - case OP_NVERIFY: - break; - case OP_OPEN: - nfsd4_encode_open(resp, op->status, &op->u.open); - break; - case OP_OPEN_CONFIRM: - nfsd4_encode_open_confirm(resp, op->status, &op->u.open_confirm); - break; - case OP_OPEN_DOWNGRADE: - nfsd4_encode_open_downgrade(resp, op->status, &op->u.open_downgrade); - break; - case OP_PUTFH: - break; - case OP_PUTROOTFH: - break; - case OP_READ: - op->status = nfsd4_encode_read(resp, op->status, &op->u.read); - break; - case OP_READDIR: - op->status = nfsd4_encode_readdir(resp, op->status, &op->u.readdir); - break; - case OP_READLINK: - op->status = nfsd4_encode_readlink(resp, op->status, &op->u.readlink); - break; - case OP_REMOVE: - nfsd4_encode_remove(resp, op->status, &op->u.remove); - break; - case OP_RENAME: - nfsd4_encode_rename(resp, op->status, &op->u.rename); - break; - case OP_RENEW: - break; - case OP_RESTOREFH: - break; - case OP_SAVEFH: - break; - case OP_SECINFO: - nfsd4_encode_secinfo(resp, op->status, &op->u.secinfo); - break; - case OP_SETATTR: - nfsd4_encode_setattr(resp, op->status, &op->u.setattr); - break; - case OP_SETCLIENTID: - nfsd4_encode_setclientid(resp, op->status, &op->u.setclientid); - break; - case OP_SETCLIENTID_CONFIRM: - break; - case OP_VERIFY: - break; - case OP_WRITE: - nfsd4_encode_write(resp, op->status, &op->u.write); - break; - case OP_RELEASE_LOCKOWNER: - break; - default: - break; - } - + if (op->opnum == OP_ILLEGAL) + goto status; + BUG_ON(op->opnum < 0 || op->opnum >= ARRAY_SIZE(nfsd4_enc_ops) || + !nfsd4_enc_ops[op->opnum]); + op->status = nfsd4_enc_ops[op->opnum](resp, op->status, &op->u); +status: /* * Note: We write the status directly, instead of using WRITE32(), * since it is already in network byte order. From 4f83aa302f8f8b42397c6d3703d670f0588c03ec Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 7 Jul 2008 15:02:02 -0400 Subject: [PATCH 41/51] nfsd: document open share bit tracking It's not immediately obvious from the code why we're doing this. Signed-off-by: J. Bruce Fields Cc: Benny Halevy --- fs/nfsd/nfs4state.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index eca8aaa450f1..c29b6ed2a0bb 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1173,6 +1173,24 @@ static inline int deny_valid(u32 x) return x <= NFS4_SHARE_DENY_BOTH; } +/* + * We store the NONE, READ, WRITE, and BOTH bits separately in the + * st_{access,deny}_bmap field of the stateid, in order to track not + * only what share bits are currently in force, but also what + * combinations of share bits previous opens have used. This allows us + * to enforce the recommendation of rfc 3530 14.2.19 that the server + * return an error if the client attempt to downgrade to a combination + * of share bits not explicable by closing some of its previous opens. + * + * XXX: This enforcement is actually incomplete, since we don't keep + * track of access/deny bit combinations; so, e.g., we allow: + * + * OPEN allow read, deny write + * OPEN allow both, deny none + * DOWNGRADE allow read, deny none + * + * which we should reject. + */ static void set_access(unsigned int *access, unsigned long bmap) { int i; From e518f0560a191269bd345178c899c790eb1ad4c8 Mon Sep 17 00:00:00 2001 From: Benny Halevy Date: Fri, 4 Jul 2008 15:38:41 +0300 Subject: [PATCH 42/51] nfsd: take file and mnt write in nfs4_upgrade_open testing with newpynfs revealed this warning: Jul 3 07:32:50 buml kernel: writeable file with no mnt_want_write() Jul 3 07:32:50 buml kernel: ------------[ cut here ]------------ Jul 3 07:32:50 buml kernel: WARNING: at /usr0/export/dev/bhalevy/git/linux-pnfs-bh-nfs41/include/linux/fs.h:855 drop_file_write_access+0x6b/0x7e() Jul 3 07:32:50 buml kernel: Modules linked in: nfsd auth_rpcgss exportfs nfs lockd nfs_acl sunrpc Jul 3 07:32:50 buml kernel: Call Trace: Jul 3 07:32:50 buml kernel: 6eaadc88: [<6002f471>] warn_on_slowpath+0x54/0x8e Jul 3 07:32:50 buml kernel: 6eaadcc8: [<601b790d>] printk+0xa0/0x793 Jul 3 07:32:50 buml kernel: 6eaadd38: [<601b6205>] __mutex_lock_slowpath+0x1db/0x1ea Jul 3 07:32:50 buml kernel: 6eaadd68: [<7107d4d5>] nfs4_preprocess_seqid_op+0x2a6/0x31c [nfsd] Jul 3 07:32:50 buml kernel: 6eaadda8: [<60078dc9>] drop_file_write_access+0x6b/0x7e Jul 3 07:32:50 buml kernel: 6eaaddc8: [<710804e4>] nfsd4_open_downgrade+0x114/0x1de [nfsd] Jul 3 07:32:50 buml kernel: 6eaade08: [<71076215>] nfsd4_proc_compound+0x1ba/0x2dc [nfsd] Jul 3 07:32:50 buml kernel: 6eaade48: [<71068221>] nfsd_dispatch+0xe5/0x1c2 [nfsd] Jul 3 07:32:50 buml kernel: 6eaade88: [<71312f81>] svc_process+0x3fd/0x714 [sunrpc] Jul 3 07:32:50 buml kernel: 6eaadea8: [<60039a81>] kernel_sigprocmask+0xf3/0x100 Jul 3 07:32:50 buml kernel: 6eaadee8: [<7106874b>] nfsd+0x182/0x29b [nfsd] Jul 3 07:32:50 buml kernel: 6eaadf48: [<60021cc9>] run_kernel_thread+0x41/0x4a Jul 3 07:32:50 buml kernel: 6eaadf58: [<710685c9>] nfsd+0x0/0x29b [nfsd] Jul 3 07:32:50 buml kernel: 6eaadf98: [<60021cb0>] run_kernel_thread+0x28/0x4a Jul 3 07:32:50 buml kernel: 6eaadfc8: [<60013829>] new_thread_handler+0x72/0x9c Jul 3 07:32:50 buml kernel: Jul 3 07:32:50 buml kernel: ---[ end trace 2426dd7cb2fba3bf ]--- Bruce Fields suggested this (Thanks!): maybe we need to be doing a mnt_want_write on open_upgrade and mnt_put_write on downgrade? This patch adds a call to mnt_want_write and file_take_write (which is doing the actual work). The counter-calls mnt_drop_write a file_release_write are now being properly called by drop_file_write_access in the exact path printed by the warning above. Signed-off-by: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c29b6ed2a0bb..1578d7a2667e 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1588,6 +1588,10 @@ nfs4_upgrade_open(struct svc_rqst *rqstp, struct svc_fh *cur_fh, struct nfs4_sta int err = get_write_access(inode); if (err) return nfserrno(err); + err = mnt_want_write(cur_fh->fh_export->ex_path.mnt); + if (err) + return nfserrno(err); + file_take_write(filp); } status = nfsd4_truncate(rqstp, cur_fh, open); if (status) { From afc1246f917c664b0df98b3c22fa62db74d2ca33 Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Fri, 11 Jul 2008 17:20:49 -0700 Subject: [PATCH 43/51] file lock: reorder struct file_lock to save space on 64 bit builds Reduce sizeof struct file_lock by 8 on 64 bit builds allowing +1 objects per slab in the file_lock_cache Signed-off-by: Richard Kennedy Signed-off-by: Andrew Morton Signed-off-by: J. Bruce Fields --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/fs.h b/include/linux/fs.h index 7c1080826832..87f89bd0f6ee 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -917,12 +917,12 @@ struct file_lock { struct list_head fl_link; /* doubly linked list of all locks */ struct list_head fl_block; /* circular list of blocked processes */ fl_owner_t fl_owner; + unsigned char fl_flags; + unsigned char fl_type; unsigned int fl_pid; struct pid *fl_nspid; wait_queue_head_t fl_wait; struct file *fl_file; - unsigned char fl_flags; - unsigned char fl_type; loff_t fl_start; loff_t fl_end; From b0e92aae157cbf78ede7b7dd03967b49fcb2102e Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 15 Jul 2008 12:35:20 -0400 Subject: [PATCH 44/51] lockd: nlm_release_host() checks for NULL, caller needn't No need to check for a NULL argument twice. Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/lockd/svc4proc.c | 3 +-- fs/lockd/svcproc.c | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 385437e3387d..006a832d46f2 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -58,8 +58,7 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, return 0; no_locks: - if (host) - nlm_release_host(host); + nlm_release_host(host); if (error) return error; return nlm_lck_denied_nolocks; diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 88379cc6e0b1..fce3d7039625 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -87,8 +87,7 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, return 0; no_locks: - if (host) - nlm_release_host(host); + nlm_release_host(host); if (error) return error; return nlm_lck_denied_nolocks; From 8f920d5e29f86d3425a68e1c3bc264d1f6f55112 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 15 Jul 2008 14:06:48 -0400 Subject: [PATCH 45/51] lockd: eliminate duplicate nlmsvc_lookup_host call from nlmsvc_testlock nlmsvc_testlock calls nlmsvc_lookup_host to find a nlm_host struct. The callers of this functions, however, call nlmsvc_retrieve_args or nlm4svc_retrieve_args, which also return a nlm_host struct. Change nlmsvc_testlock to take a host arg instead of calling nlmsvc_lookup_host itself and change the callers to pass a pointer to the nlm_host they've already found. We take a reference to host in the place where nlmsvc_testlock() previous did a new lookup, so the reference counting is unchanged from before. Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/lockd/svc4proc.c | 2 +- fs/lockd/svclock.c | 12 +++--------- fs/lockd/svcproc.c | 2 +- include/linux/lockd/lockd.h | 3 ++- 4 files changed, 7 insertions(+), 12 deletions(-) diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 006a832d46f2..8cfb9daa7c77 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -99,7 +99,7 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success; /* Now check for conflicting locks */ - resp->status = nlmsvc_testlock(rqstp, file, &argp->lock, &resp->lock, &resp->cookie); + resp->status = nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock, &resp->cookie); if (resp->status == nlm_drop_reply) rc = rpc_drop_reply; else diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 81aca859bfde..f40afb3a0e69 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -460,8 +460,8 @@ out: */ __be32 nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, - struct nlm_lock *lock, struct nlm_lock *conflock, - struct nlm_cookie *cookie) + struct nlm_host *host, struct nlm_lock *lock, + struct nlm_lock *conflock, struct nlm_cookie *cookie) { struct nlm_block *block = NULL; int error; @@ -479,16 +479,10 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, if (block == NULL) { struct file_lock *conf = kzalloc(sizeof(*conf), GFP_KERNEL); - struct nlm_host *host; if (conf == NULL) return nlm_granted; - /* Create host handle for callback */ - host = nlmsvc_lookup_host(rqstp, lock->caller, lock->len); - if (host == NULL) { - kfree(conf); - return nlm_lck_denied_nolocks; - } + nlm_get_host(host); block = nlmsvc_create_block(rqstp, host, file, lock, cookie); if (block == NULL) { kfree(conf); diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index fce3d7039625..e099f589b61b 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -128,7 +128,7 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success; /* Now check for conflicting locks */ - resp->status = cast_status(nlmsvc_testlock(rqstp, file, &argp->lock, &resp->lock, &resp->cookie)); + resp->status = cast_status(nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock, &resp->cookie)); if (resp->status == nlm_drop_reply) rc = rpc_drop_reply; else diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 102d928f7206..b27967034b53 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -203,7 +203,8 @@ __be32 nlmsvc_lock(struct svc_rqst *, struct nlm_file *, struct nlm_lock *, int, struct nlm_cookie *); __be32 nlmsvc_unlock(struct nlm_file *, struct nlm_lock *); __be32 nlmsvc_testlock(struct svc_rqst *, struct nlm_file *, - struct nlm_lock *, struct nlm_lock *, struct nlm_cookie *); + struct nlm_host *, struct nlm_lock *, + struct nlm_lock *, struct nlm_cookie *); __be32 nlmsvc_cancel_blocked(struct nlm_file *, struct nlm_lock *); unsigned long nlmsvc_retry_blocked(void); void nlmsvc_traverse_blocks(struct nlm_host *, struct nlm_file *, From 6cde4de80773497d8333985b135f472eda870904 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 15 Jul 2008 14:26:17 -0400 Subject: [PATCH 46/51] lockd: eliminate duplicate nlmsvc_lookup_host call from nlmsvc_lock nlmsvc_lock calls nlmsvc_lookup_host to find a nlm_host struct. The callers of this function, however, call nlmsvc_retrieve_args or nlm4svc_retrieve_args, which also return a nlm_host struct. Change nlmsvc_lock to take a host arg instead of calling nlmsvc_lookup_host itself and change the callers to pass a pointer to the nlm_host they've already found. Since nlmsvc_testlock() now just uses the caller's reference, we no longer need to get or release it. Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/lockd/svc4proc.c | 2 +- fs/lockd/svclock.c | 10 ++-------- fs/lockd/svcproc.c | 2 +- include/linux/lockd/lockd.h | 3 ++- 4 files changed, 6 insertions(+), 11 deletions(-) diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 8cfb9daa7c77..189b2ce01da6 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -145,7 +145,7 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, #endif /* Now try to lock the file */ - resp->status = nlmsvc_lock(rqstp, file, &argp->lock, + resp->status = nlmsvc_lock(rqstp, file, host, &argp->lock, argp->block, &argp->cookie); if (resp->status == nlm_drop_reply) rc = rpc_drop_reply; diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index f40afb3a0e69..bcf73f6e8226 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -358,10 +358,10 @@ nlmsvc_defer_lock_rqst(struct svc_rqst *rqstp, struct nlm_block *block) */ __be32 nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, - struct nlm_lock *lock, int wait, struct nlm_cookie *cookie) + struct nlm_host *host, struct nlm_lock *lock, int wait, + struct nlm_cookie *cookie) { struct nlm_block *block = NULL; - struct nlm_host *host; int error; __be32 ret; @@ -373,11 +373,6 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, (long long)lock->fl.fl_end, wait); - /* Create host handle for callback */ - host = nlmsvc_lookup_host(rqstp, lock->caller, lock->len); - if (host == NULL) - return nlm_lck_denied_nolocks; - /* Lock file against concurrent access */ mutex_lock(&file->f_mutex); /* Get existing block (in case client is busy-waiting) @@ -450,7 +445,6 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, out: mutex_unlock(&file->f_mutex); nlmsvc_release_block(block); - nlm_release_host(host); dprintk("lockd: nlmsvc_lock returned %u\n", ret); return ret; } diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index e099f589b61b..82dc9083ba67 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -175,7 +175,7 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, #endif /* Now try to lock the file */ - resp->status = cast_status(nlmsvc_lock(rqstp, file, &argp->lock, + resp->status = cast_status(nlmsvc_lock(rqstp, file, host, &argp->lock, argp->block, &argp->cookie)); if (resp->status == nlm_drop_reply) rc = rpc_drop_reply; diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index b27967034b53..f81f9dd5f147 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -200,7 +200,8 @@ typedef int (*nlm_host_match_fn_t)(void *cur, struct nlm_host *ref); * Server-side lock handling */ __be32 nlmsvc_lock(struct svc_rqst *, struct nlm_file *, - struct nlm_lock *, int, struct nlm_cookie *); + struct nlm_host *, struct nlm_lock *, int, + struct nlm_cookie *); __be32 nlmsvc_unlock(struct nlm_file *, struct nlm_lock *); __be32 nlmsvc_testlock(struct svc_rqst *, struct nlm_file *, struct nlm_host *, struct nlm_lock *, From 6d7bbbbacc5202eaabbc232681cc325b22a73eeb Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 15 Jul 2008 14:38:32 -0400 Subject: [PATCH 47/51] lockd: minor svclock.c style fixes Signed-off-by: J. Bruce Fields --- fs/lockd/svclock.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index bcf73f6e8226..51a0dea0ae8a 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -129,9 +129,9 @@ nlmsvc_lookup_block(struct nlm_file *file, struct nlm_lock *lock) static inline int nlm_cookie_match(struct nlm_cookie *a, struct nlm_cookie *b) { - if(a->len != b->len) + if (a->len != b->len) return 0; - if(memcmp(a->data,b->data,a->len)) + if (memcmp(a->data, b->data, a->len)) return 0; return 1; } @@ -381,7 +381,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, block = nlmsvc_lookup_block(file, lock); if (block == NULL) { block = nlmsvc_create_block(rqstp, nlm_get_host(host), file, - lock, cookie); + lock, cookie); ret = nlm_lck_denied_nolocks; if (block == NULL) goto out; @@ -412,7 +412,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, lock->fl.fl_flags &= ~FL_SLEEP; dprintk("lockd: vfs_lock_file returned %d\n", error); - switch(error) { + switch (error) { case 0: ret = nlm_granted; goto out; @@ -880,7 +880,7 @@ nlmsvc_retry_blocked(void) if (block->b_when == NLM_NEVER) break; - if (time_after(block->b_when,jiffies)) { + if (time_after(block->b_when, jiffies)) { timeout = block->b_when - jiffies; break; } From 560de0e65904db392e1c443c4bf5ee750573336b Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 15 Jul 2008 15:05:45 -0400 Subject: [PATCH 48/51] lockd: get host reference in nlmsvc_create_block() instead of callers It may not be obvious (till you look at the definition of nlm_alloc_call()) that a function like nlmsvc_create_block() should consume a reference on success or failure, so I find it clearer if it takes the reference it needs itself. And both callers already do this immediately before the call anyway. Signed-off-by: J. Bruce Fields --- fs/lockd/svclock.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 51a0dea0ae8a..b8f86b73a85d 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -180,6 +180,7 @@ nlmsvc_create_block(struct svc_rqst *rqstp, struct nlm_host *host, struct nlm_block *block; struct nlm_rqst *call = NULL; + nlm_get_host(host); call = nlm_alloc_call(host); if (call == NULL) return NULL; @@ -380,8 +381,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, */ block = nlmsvc_lookup_block(file, lock); if (block == NULL) { - block = nlmsvc_create_block(rqstp, nlm_get_host(host), file, - lock, cookie); + block = nlmsvc_create_block(rqstp, host, file, lock, cookie); ret = nlm_lck_denied_nolocks; if (block == NULL) goto out; @@ -476,7 +476,6 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, if (conf == NULL) return nlm_granted; - nlm_get_host(host); block = nlmsvc_create_block(rqstp, host, file, lock, cookie); if (block == NULL) { kfree(conf); From 367c8c7bd9a2882daad6c9cb607e1db8ef781ad4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 30 Jun 2008 18:58:14 -0400 Subject: [PATCH 49/51] lockd: Pass "struct sockaddr *" to new failover-by-IP function Pass a more generic socket address type to nlmsvc_unlock_all_by_ip() to allow for future support of IPv6. Also provide additional sanity checking in failover_unlock_ip() when constructing the server's IP address. As an added bonus, provide clean kerneldoc comments on related NLM interfaces which were recently added. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- fs/lockd/svcsubs.c | 32 +++++++++++++++++++++++--------- fs/nfsd/nfsctl.c | 15 ++++++++++----- include/linux/lockd/lockd.h | 2 +- 3 files changed, 34 insertions(+), 15 deletions(-) diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index d1c48b539df8..198b4e55b373 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -373,13 +373,16 @@ nlmsvc_free_host_resources(struct nlm_host *host) } } -/* - * Remove all locks held for clients +/** + * nlmsvc_invalidate_all - remove all locks held for clients + * + * Release all locks held by NFS clients. + * */ void nlmsvc_invalidate_all(void) { - /* Release all locks held by NFS clients. + /* * Previously, the code would call * nlmsvc_free_host_resources for each client in * turn, which is about as inefficient as it gets. @@ -396,6 +399,12 @@ nlmsvc_match_sb(void *datap, struct nlm_file *file) return sb == file->f_file->f_path.mnt->mnt_sb; } +/** + * nlmsvc_unlock_all_by_sb - release locks held on this file system + * @sb: super block + * + * Release all locks held by clients accessing this file system. + */ int nlmsvc_unlock_all_by_sb(struct super_block *sb) { @@ -409,17 +418,22 @@ EXPORT_SYMBOL_GPL(nlmsvc_unlock_all_by_sb); static int nlmsvc_match_ip(void *datap, struct nlm_host *host) { - __be32 *server_addr = datap; - - return host->h_saddr.sin_addr.s_addr == *server_addr; + return nlm_cmp_addr(&host->h_saddr, datap); } +/** + * nlmsvc_unlock_all_by_ip - release local locks by IP address + * @server_addr: server's IP address as seen by clients + * + * Release all locks held by clients accessing this host + * via the passed in IP address. + */ int -nlmsvc_unlock_all_by_ip(__be32 server_addr) +nlmsvc_unlock_all_by_ip(struct sockaddr *server_addr) { int ret; - ret = nlm_traverse_files(&server_addr, nlmsvc_match_ip, NULL); - return ret ? -EIO : 0; + ret = nlm_traverse_files(server_addr, nlmsvc_match_ip, NULL); + return ret ? -EIO : 0; } EXPORT_SYMBOL_GPL(nlmsvc_unlock_all_by_ip); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 2c2eb8796c10..1955a2702e60 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -310,9 +310,12 @@ static ssize_t write_getfd(struct file *file, char *buf, size_t size) static ssize_t failover_unlock_ip(struct file *file, char *buf, size_t size) { - __be32 server_ip; - char *fo_path, c; + struct sockaddr_in sin = { + .sin_family = AF_INET, + }; int b1, b2, b3, b4; + char c; + char *fo_path; /* sanity check */ if (size == 0) @@ -326,11 +329,13 @@ static ssize_t failover_unlock_ip(struct file *file, char *buf, size_t size) return -EINVAL; /* get ipv4 address */ - if (sscanf(fo_path, "%u.%u.%u.%u%c", &b1, &b2, &b3, &b4, &c) != 4) + if (sscanf(fo_path, NIPQUAD_FMT "%c", &b1, &b2, &b3, &b4, &c) != 4) return -EINVAL; - server_ip = htonl((((((b1<<8)|b2)<<8)|b3)<<8)|b4); + if (b1 > 255 || b2 > 255 || b3 > 255 || b4 > 255) + return -EINVAL; + sin.sin_addr.s_addr = htonl((b1 << 24) | (b2 << 16) | (b3 << 8) | b4); - return nlmsvc_unlock_all_by_ip(server_ip); + return nlmsvc_unlock_all_by_ip((struct sockaddr *)&sin); } static ssize_t failover_unlock_fs(struct file *file, char *buf, size_t size) diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index f81f9dd5f147..dbb87ab282e8 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -226,7 +226,7 @@ void nlmsvc_invalidate_all(void); * Cluster failover support */ int nlmsvc_unlock_all_by_sb(struct super_block *sb); -int nlmsvc_unlock_all_by_ip(__be32 server_addr); +int nlmsvc_unlock_all_by_ip(struct sockaddr *server_addr); static inline struct inode *nlmsvc_file_inode(struct nlm_file *file) { From ad1060c89cfe451de849373d98e42fad58dd25ae Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Fri, 18 Jul 2008 15:04:16 -0400 Subject: [PATCH 50/51] nfsd: Use C99 initializers in fs/nfsd/nfs4xdr.c Thanks to problem report and original patch from Harvey Harrison. Signed-off-by: J. Bruce Fields Cc: Harvey Harrison Cc: Benny Halevy --- fs/nfsd/nfs4xdr.c | 148 +++++++++++++++++++++++----------------------- 1 file changed, 74 insertions(+), 74 deletions(-) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 9b6a9bafc6b4..d4b9d09a6683 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1000,43 +1000,43 @@ nfsd4_decode_notsupp(struct nfsd4_compoundargs *argp, void *p) typedef __be32(*nfsd4_dec)(struct nfsd4_compoundargs *argp, void *); static nfsd4_dec nfsd4_dec_ops[] = { - [OP_ACCESS] (nfsd4_dec)nfsd4_decode_access, - [OP_CLOSE] (nfsd4_dec)nfsd4_decode_close, - [OP_COMMIT] (nfsd4_dec)nfsd4_decode_commit, - [OP_CREATE] (nfsd4_dec)nfsd4_decode_create, - [OP_DELEGPURGE] (nfsd4_dec)nfsd4_decode_notsupp, - [OP_DELEGRETURN] (nfsd4_dec)nfsd4_decode_delegreturn, - [OP_GETATTR] (nfsd4_dec)nfsd4_decode_getattr, - [OP_GETFH] (nfsd4_dec)nfsd4_decode_noop, - [OP_LINK] (nfsd4_dec)nfsd4_decode_link, - [OP_LOCK] (nfsd4_dec)nfsd4_decode_lock, - [OP_LOCKT] (nfsd4_dec)nfsd4_decode_lockt, - [OP_LOCKU] (nfsd4_dec)nfsd4_decode_locku, - [OP_LOOKUP] (nfsd4_dec)nfsd4_decode_lookup, - [OP_LOOKUPP] (nfsd4_dec)nfsd4_decode_noop, - [OP_NVERIFY] (nfsd4_dec)nfsd4_decode_verify, - [OP_OPEN] (nfsd4_dec)nfsd4_decode_open, - [OP_OPENATTR] (nfsd4_dec)nfsd4_decode_notsupp, - [OP_OPEN_CONFIRM] (nfsd4_dec)nfsd4_decode_open_confirm, - [OP_OPEN_DOWNGRADE] (nfsd4_dec)nfsd4_decode_open_downgrade, - [OP_PUTFH] (nfsd4_dec)nfsd4_decode_putfh, - [OP_PUTPUBFH] (nfsd4_dec)nfsd4_decode_notsupp, - [OP_PUTROOTFH] (nfsd4_dec)nfsd4_decode_noop, - [OP_READ] (nfsd4_dec)nfsd4_decode_read, - [OP_READDIR] (nfsd4_dec)nfsd4_decode_readdir, - [OP_READLINK] (nfsd4_dec)nfsd4_decode_noop, - [OP_REMOVE] (nfsd4_dec)nfsd4_decode_remove, - [OP_RENAME] (nfsd4_dec)nfsd4_decode_rename, - [OP_RENEW] (nfsd4_dec)nfsd4_decode_renew, - [OP_RESTOREFH] (nfsd4_dec)nfsd4_decode_noop, - [OP_SAVEFH] (nfsd4_dec)nfsd4_decode_noop, - [OP_SECINFO] (nfsd4_dec)nfsd4_decode_secinfo, - [OP_SETATTR] (nfsd4_dec)nfsd4_decode_setattr, - [OP_SETCLIENTID] (nfsd4_dec)nfsd4_decode_setclientid, - [OP_SETCLIENTID_CONFIRM](nfsd4_dec)nfsd4_decode_setclientid_confirm, - [OP_VERIFY] (nfsd4_dec)nfsd4_decode_verify, - [OP_WRITE] (nfsd4_dec)nfsd4_decode_write, - [OP_RELEASE_LOCKOWNER] (nfsd4_dec)nfsd4_decode_release_lockowner, + [OP_ACCESS] = (nfsd4_dec)nfsd4_decode_access, + [OP_CLOSE] = (nfsd4_dec)nfsd4_decode_close, + [OP_COMMIT] = (nfsd4_dec)nfsd4_decode_commit, + [OP_CREATE] = (nfsd4_dec)nfsd4_decode_create, + [OP_DELEGPURGE] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_DELEGRETURN] = (nfsd4_dec)nfsd4_decode_delegreturn, + [OP_GETATTR] = (nfsd4_dec)nfsd4_decode_getattr, + [OP_GETFH] = (nfsd4_dec)nfsd4_decode_noop, + [OP_LINK] = (nfsd4_dec)nfsd4_decode_link, + [OP_LOCK] = (nfsd4_dec)nfsd4_decode_lock, + [OP_LOCKT] = (nfsd4_dec)nfsd4_decode_lockt, + [OP_LOCKU] = (nfsd4_dec)nfsd4_decode_locku, + [OP_LOOKUP] = (nfsd4_dec)nfsd4_decode_lookup, + [OP_LOOKUPP] = (nfsd4_dec)nfsd4_decode_noop, + [OP_NVERIFY] = (nfsd4_dec)nfsd4_decode_verify, + [OP_OPEN] = (nfsd4_dec)nfsd4_decode_open, + [OP_OPENATTR] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_OPEN_CONFIRM] = (nfsd4_dec)nfsd4_decode_open_confirm, + [OP_OPEN_DOWNGRADE] = (nfsd4_dec)nfsd4_decode_open_downgrade, + [OP_PUTFH] = (nfsd4_dec)nfsd4_decode_putfh, + [OP_PUTPUBFH] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_PUTROOTFH] = (nfsd4_dec)nfsd4_decode_noop, + [OP_READ] = (nfsd4_dec)nfsd4_decode_read, + [OP_READDIR] = (nfsd4_dec)nfsd4_decode_readdir, + [OP_READLINK] = (nfsd4_dec)nfsd4_decode_noop, + [OP_REMOVE] = (nfsd4_dec)nfsd4_decode_remove, + [OP_RENAME] = (nfsd4_dec)nfsd4_decode_rename, + [OP_RENEW] = (nfsd4_dec)nfsd4_decode_renew, + [OP_RESTOREFH] = (nfsd4_dec)nfsd4_decode_noop, + [OP_SAVEFH] = (nfsd4_dec)nfsd4_decode_noop, + [OP_SECINFO] = (nfsd4_dec)nfsd4_decode_secinfo, + [OP_SETATTR] = (nfsd4_dec)nfsd4_decode_setattr, + [OP_SETCLIENTID] = (nfsd4_dec)nfsd4_decode_setclientid, + [OP_SETCLIENTID_CONFIRM] = (nfsd4_dec)nfsd4_decode_setclientid_confirm, + [OP_VERIFY] = (nfsd4_dec)nfsd4_decode_verify, + [OP_WRITE] = (nfsd4_dec)nfsd4_decode_write, + [OP_RELEASE_LOCKOWNER] = (nfsd4_dec)nfsd4_decode_release_lockowner, }; struct nfsd4_minorversion_ops { @@ -1045,7 +1045,7 @@ struct nfsd4_minorversion_ops { }; static struct nfsd4_minorversion_ops nfsd4_minorversion[] = { - [0] { nfsd4_dec_ops, ARRAY_SIZE(nfsd4_dec_ops) }, + [0] = { nfsd4_dec_ops, ARRAY_SIZE(nfsd4_dec_ops) }, }; static __be32 @@ -2577,42 +2577,42 @@ nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p) typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *); static nfsd4_enc nfsd4_enc_ops[] = { - [OP_ACCESS] (nfsd4_enc)nfsd4_encode_access, - [OP_CLOSE] (nfsd4_enc)nfsd4_encode_close, - [OP_COMMIT] (nfsd4_enc)nfsd4_encode_commit, - [OP_CREATE] (nfsd4_enc)nfsd4_encode_create, - [OP_DELEGPURGE] (nfsd4_enc)nfsd4_encode_noop, - [OP_DELEGRETURN] (nfsd4_enc)nfsd4_encode_noop, - [OP_GETATTR] (nfsd4_enc)nfsd4_encode_getattr, - [OP_GETFH] (nfsd4_enc)nfsd4_encode_getfh, - [OP_LINK] (nfsd4_enc)nfsd4_encode_link, - [OP_LOCK] (nfsd4_enc)nfsd4_encode_lock, - [OP_LOCKT] (nfsd4_enc)nfsd4_encode_lockt, - [OP_LOCKU] (nfsd4_enc)nfsd4_encode_locku, - [OP_LOOKUP] (nfsd4_enc)nfsd4_encode_noop, - [OP_LOOKUPP] (nfsd4_enc)nfsd4_encode_noop, - [OP_NVERIFY] (nfsd4_enc)nfsd4_encode_noop, - [OP_OPEN] (nfsd4_enc)nfsd4_encode_open, - [OP_OPEN_CONFIRM] (nfsd4_enc)nfsd4_encode_open_confirm, - [OP_OPEN_DOWNGRADE] (nfsd4_enc)nfsd4_encode_open_downgrade, - [OP_PUTFH] (nfsd4_enc)nfsd4_encode_noop, - [OP_PUTPUBFH] (nfsd4_enc)nfsd4_encode_noop, - [OP_PUTROOTFH] (nfsd4_enc)nfsd4_encode_noop, - [OP_READ] (nfsd4_enc)nfsd4_encode_read, - [OP_READDIR] (nfsd4_enc)nfsd4_encode_readdir, - [OP_READLINK] (nfsd4_enc)nfsd4_encode_readlink, - [OP_REMOVE] (nfsd4_enc)nfsd4_encode_remove, - [OP_RENAME] (nfsd4_enc)nfsd4_encode_rename, - [OP_RENEW] (nfsd4_enc)nfsd4_encode_noop, - [OP_RESTOREFH] (nfsd4_enc)nfsd4_encode_noop, - [OP_SAVEFH] (nfsd4_enc)nfsd4_encode_noop, - [OP_SECINFO] (nfsd4_enc)nfsd4_encode_secinfo, - [OP_SETATTR] (nfsd4_enc)nfsd4_encode_setattr, - [OP_SETCLIENTID] (nfsd4_enc)nfsd4_encode_setclientid, - [OP_SETCLIENTID_CONFIRM](nfsd4_enc)nfsd4_encode_noop, - [OP_VERIFY] (nfsd4_enc)nfsd4_encode_noop, - [OP_WRITE] (nfsd4_enc)nfsd4_encode_write, - [OP_RELEASE_LOCKOWNER] (nfsd4_enc)nfsd4_encode_noop, + [OP_ACCESS] = (nfsd4_enc)nfsd4_encode_access, + [OP_CLOSE] = (nfsd4_enc)nfsd4_encode_close, + [OP_COMMIT] = (nfsd4_enc)nfsd4_encode_commit, + [OP_CREATE] = (nfsd4_enc)nfsd4_encode_create, + [OP_DELEGPURGE] = (nfsd4_enc)nfsd4_encode_noop, + [OP_DELEGRETURN] = (nfsd4_enc)nfsd4_encode_noop, + [OP_GETATTR] = (nfsd4_enc)nfsd4_encode_getattr, + [OP_GETFH] = (nfsd4_enc)nfsd4_encode_getfh, + [OP_LINK] = (nfsd4_enc)nfsd4_encode_link, + [OP_LOCK] = (nfsd4_enc)nfsd4_encode_lock, + [OP_LOCKT] = (nfsd4_enc)nfsd4_encode_lockt, + [OP_LOCKU] = (nfsd4_enc)nfsd4_encode_locku, + [OP_LOOKUP] = (nfsd4_enc)nfsd4_encode_noop, + [OP_LOOKUPP] = (nfsd4_enc)nfsd4_encode_noop, + [OP_NVERIFY] = (nfsd4_enc)nfsd4_encode_noop, + [OP_OPEN] = (nfsd4_enc)nfsd4_encode_open, + [OP_OPEN_CONFIRM] = (nfsd4_enc)nfsd4_encode_open_confirm, + [OP_OPEN_DOWNGRADE] = (nfsd4_enc)nfsd4_encode_open_downgrade, + [OP_PUTFH] = (nfsd4_enc)nfsd4_encode_noop, + [OP_PUTPUBFH] = (nfsd4_enc)nfsd4_encode_noop, + [OP_PUTROOTFH] = (nfsd4_enc)nfsd4_encode_noop, + [OP_READ] = (nfsd4_enc)nfsd4_encode_read, + [OP_READDIR] = (nfsd4_enc)nfsd4_encode_readdir, + [OP_READLINK] = (nfsd4_enc)nfsd4_encode_readlink, + [OP_REMOVE] = (nfsd4_enc)nfsd4_encode_remove, + [OP_RENAME] = (nfsd4_enc)nfsd4_encode_rename, + [OP_RENEW] = (nfsd4_enc)nfsd4_encode_noop, + [OP_RESTOREFH] = (nfsd4_enc)nfsd4_encode_noop, + [OP_SAVEFH] = (nfsd4_enc)nfsd4_encode_noop, + [OP_SECINFO] = (nfsd4_enc)nfsd4_encode_secinfo, + [OP_SETATTR] = (nfsd4_enc)nfsd4_encode_setattr, + [OP_SETCLIENTID] = (nfsd4_enc)nfsd4_encode_setclientid, + [OP_SETCLIENTID_CONFIRM] = (nfsd4_enc)nfsd4_encode_noop, + [OP_VERIFY] = (nfsd4_enc)nfsd4_encode_noop, + [OP_WRITE] = (nfsd4_enc)nfsd4_encode_write, + [OP_RELEASE_LOCKOWNER] = (nfsd4_enc)nfsd4_encode_noop, }; void From 5108b27651727b5aba0826e8fd7be71b42428701 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Thu, 17 Jul 2008 21:33:04 -0700 Subject: [PATCH 51/51] nfsd: nfs4xdr.c do-while is not a compound statement The WRITEMEM macro produces sparse warnings of the form: fs/nfsd/nfs4xdr.c:2668:2: warning: do-while statement is not a compound statement Signed-off-by: Harvey Harrison Cc: Benny Halevy Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index d4b9d09a6683..14ba4d9b2859 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1160,11 +1160,11 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) *p++ = htonl((u32)((n) >> 32)); \ *p++ = htonl((u32)(n)); \ } while (0) -#define WRITEMEM(ptr,nbytes) do if (nbytes > 0) { \ +#define WRITEMEM(ptr,nbytes) do { if (nbytes > 0) { \ *(p + XDR_QUADLEN(nbytes) -1) = 0; \ memcpy(p, ptr, nbytes); \ p += XDR_QUADLEN(nbytes); \ -} while (0) +}} while (0) #define WRITECINFO(c) do { \ *p++ = htonl(c.atomic); \ *p++ = htonl(c.before_ctime_sec); \