From c3f52af3e03013db5237e339c817beaae5ec9e3a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 3 Sep 2012 14:56:02 -0400 Subject: NFS: Fix the initialisation of the readdir 'cookieverf' array When the NFS_COOKIEVERF helper macro was converted into a static inline function in commit 99fadcd764 (nfs: convert NFS_*(inode) helpers to static inline), we broke the initialisation of the readdir cookies, since that depended on doing a memset with an argument of 'sizeof(NFS_COOKIEVERF(inode))' which therefore changed from sizeof(be32 cookieverf[2]) to sizeof(be32 *). At this point, NFS_COOKIEVERF seems to be more of an obfuscation than a helper, so the best thing would be to just get rid of it. Also see: https://bugzilla.kernel.org/show_bug.cgi?id=46881 Reported-by: Andi Kleen Reported-by: David Binderman Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org --- include/linux/nfs_fs.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 1f8fc7f9bcd8..4b03f56e280e 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -265,11 +265,6 @@ static inline const struct nfs_rpc_ops *NFS_PROTO(const struct inode *inode) return NFS_SERVER(inode)->nfs_client->rpc_ops; } -static inline __be32 *NFS_COOKIEVERF(const struct inode *inode) -{ - return NFS_I(inode)->cookieverf; -} - static inline unsigned NFS_MINATTRTIMEO(const struct inode *inode) { struct nfs_server *nfss = NFS_SERVER(inode); -- cgit v1.2.3-59-g8ed1b From 1f1ea6c2d9d8c0be9ec56454b05315273b5de8ce Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 26 Aug 2012 11:44:43 -0700 Subject: NFSv4: Fix buffer overflow checking in __nfs4_get_acl_uncached Pass the checks made by decode_getacl back to __nfs4_get_acl_uncached so that it knows if the acl has been truncated. The current overflow checking is broken, resulting in Oopses on user-triggered nfs4_getfacl calls, and is opaque to the point where several attempts at fixing it have failed. This patch tries to clean up the code in addition to fixing the Oopses by ensuring that the overflow checks are performed in a single place (decode_getacl). If the overflow check failed, we will still be able to report the acl length, but at least we will no longer attempt to cache the acl or copy the truncated contents to user space. Reported-by: Sachin Prabhu Signed-off-by: Trond Myklebust Tested-by: Sachin Prabhu --- fs/nfs/nfs4proc.c | 31 ++++++++++++------------------- fs/nfs/nfs4xdr.c | 14 +++++--------- include/linux/nfs_xdr.h | 2 +- 3 files changed, 18 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6b94f2d52532..1e50326d00dd 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3739,7 +3739,7 @@ static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size struct nfs4_cached_acl *acl; size_t buflen = sizeof(*acl) + acl_len; - if (pages && buflen <= PAGE_SIZE) { + if (buflen <= PAGE_SIZE) { acl = kmalloc(buflen, GFP_KERNEL); if (acl == NULL) goto out; @@ -3784,7 +3784,6 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu }; unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE); int ret = -ENOMEM, i; - size_t acl_len = 0; /* As long as we're doing a round trip to the server anyway, * let's be prepared for a page of acl data. */ @@ -3807,11 +3806,6 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu args.acl_len = npages * PAGE_SIZE; args.acl_pgbase = 0; - /* Let decode_getfacl know not to fail if the ACL data is larger than - * the page we send as a guess */ - if (buf == NULL) - res.acl_flags |= NFS4_ACL_LEN_REQUEST; - dprintk("%s buf %p buflen %zu npages %d args.acl_len %zu\n", __func__, buf, buflen, npages, args.acl_len); ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode), @@ -3819,20 +3813,19 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu if (ret) goto out_free; - acl_len = res.acl_len; - if (acl_len > args.acl_len) - nfs4_write_cached_acl(inode, NULL, 0, acl_len); - else - nfs4_write_cached_acl(inode, pages, res.acl_data_offset, - acl_len); - if (buf) { + /* Handle the case where the passed-in buffer is too short */ + if (res.acl_flags & NFS4_ACL_TRUNC) { + /* Did the user only issue a request for the acl length? */ + if (buf == NULL) + goto out_ok; ret = -ERANGE; - if (acl_len > buflen) - goto out_free; - _copy_from_pages(buf, pages, res.acl_data_offset, - acl_len); + goto out_free; } - ret = acl_len; + nfs4_write_cached_acl(inode, pages, res.acl_data_offset, res.acl_len); + if (buf) + _copy_from_pages(buf, pages, res.acl_data_offset, res.acl_len); +out_ok: + ret = res.acl_len; out_free: for (i = 0; i < npages; i++) if (pages[i]) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 1bfbd67c556d..541e796e6db5 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -5072,18 +5072,14 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, * are stored with the acl data to handle the problem of * variable length bitmaps.*/ res->acl_data_offset = xdr_stream_pos(xdr) - pg_offset; - - /* We ignore &savep and don't do consistency checks on - * the attr length. Let userspace figure it out.... */ res->acl_len = attrlen; - if (attrlen > (xdr->nwords << 2)) { - if (res->acl_flags & NFS4_ACL_LEN_REQUEST) { - /* getxattr interface called with a NULL buf */ - goto out; - } + + /* Check for receive buffer overflow */ + if (res->acl_len > (xdr->nwords << 2) || + res->acl_len + res->acl_data_offset > xdr->buf->page_len) { + res->acl_flags |= NFS4_ACL_TRUNC; dprintk("NFS: acl reply: attrlen %u > page_len %u\n", attrlen, xdr->nwords << 2); - return -EINVAL; } } else status = -EOPNOTSUPP; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index ac7c8ae254f2..be9cf3c7e79e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -652,7 +652,7 @@ struct nfs_getaclargs { }; /* getxattr ACL interface flags */ -#define NFS4_ACL_LEN_REQUEST 0x0001 /* zero length getxattr buffer */ +#define NFS4_ACL_TRUNC 0x0001 /* ACL was truncated */ struct nfs_getaclres { size_t acl_len; size_t acl_data_offset; -- cgit v1.2.3-59-g8ed1b From f39c1bfb5a03e2d255451bff05be0d7255298fa4 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 7 Sep 2012 11:08:50 -0400 Subject: SUNRPC: Fix a UDP transport regression Commit 43cedbf0e8dfb9c5610eb7985d5f21263e313802 (SUNRPC: Ensure that we grab the XPRT_LOCK before calling xprt_alloc_slot) is causing hangs in the case of NFS over UDP mounts. Since neither the UDP or the RDMA transport mechanism use dynamic slot allocation, we can skip grabbing the socket lock for those transports. Add a new rpc_xprt_op to allow switching between the TCP and UDP/RDMA case. Note that the NFSv4.1 back channel assigns the slot directly through rpc_run_bc_task, so we can ignore that case. Reported-by: Dick Streefland Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org [>= 3.1] --- include/linux/sunrpc/xprt.h | 3 +++ net/sunrpc/xprt.c | 34 ++++++++++++++++++++-------------- net/sunrpc/xprtrdma/transport.c | 1 + net/sunrpc/xprtsock.c | 3 +++ 4 files changed, 27 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index cff40aa7db62..bf8c49ff7530 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -114,6 +114,7 @@ struct rpc_xprt_ops { void (*set_buffer_size)(struct rpc_xprt *xprt, size_t sndsize, size_t rcvsize); int (*reserve_xprt)(struct rpc_xprt *xprt, struct rpc_task *task); void (*release_xprt)(struct rpc_xprt *xprt, struct rpc_task *task); + void (*alloc_slot)(struct rpc_xprt *xprt, struct rpc_task *task); void (*rpcbind)(struct rpc_task *task); void (*set_port)(struct rpc_xprt *xprt, unsigned short port); void (*connect)(struct rpc_task *task); @@ -281,6 +282,8 @@ void xprt_connect(struct rpc_task *task); void xprt_reserve(struct rpc_task *task); int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task); int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); +void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); +void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); int xprt_prepare_transmit(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); void xprt_end_transmit(struct rpc_task *task); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index a5a402a7d21f..5d7f61d7559c 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -969,11 +969,11 @@ static bool xprt_dynamic_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req) return false; } -static void xprt_alloc_slot(struct rpc_task *task) +void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task) { - struct rpc_xprt *xprt = task->tk_xprt; struct rpc_rqst *req; + spin_lock(&xprt->reserve_lock); if (!list_empty(&xprt->free)) { req = list_entry(xprt->free.next, struct rpc_rqst, rq_list); list_del(&req->rq_list); @@ -994,12 +994,29 @@ static void xprt_alloc_slot(struct rpc_task *task) default: task->tk_status = -EAGAIN; } + spin_unlock(&xprt->reserve_lock); return; out_init_req: task->tk_status = 0; task->tk_rqstp = req; xprt_request_init(task, xprt); + spin_unlock(&xprt->reserve_lock); +} +EXPORT_SYMBOL_GPL(xprt_alloc_slot); + +void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task) +{ + /* Note: grabbing the xprt_lock_write() ensures that we throttle + * new slot allocation if the transport is congested (i.e. when + * reconnecting a stream transport or when out of socket write + * buffer space). + */ + if (xprt_lock_write(xprt, task)) { + xprt_alloc_slot(xprt, task); + xprt_release_write(xprt, task); + } } +EXPORT_SYMBOL_GPL(xprt_lock_and_alloc_slot); static void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req) { @@ -1083,20 +1100,9 @@ void xprt_reserve(struct rpc_task *task) if (task->tk_rqstp != NULL) return; - /* Note: grabbing the xprt_lock_write() here is not strictly needed, - * but ensures that we throttle new slot allocation if the transport - * is congested (e.g. if reconnecting or if we're out of socket - * write buffer space). - */ task->tk_timeout = 0; task->tk_status = -EAGAIN; - if (!xprt_lock_write(xprt, task)) - return; - - spin_lock(&xprt->reserve_lock); - xprt_alloc_slot(task); - spin_unlock(&xprt->reserve_lock); - xprt_release_write(xprt, task); + xprt->ops->alloc_slot(xprt, task); } static inline __be32 xprt_alloc_xid(struct rpc_xprt *xprt) diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 06cdbff79e4a..5d9202dc7cb1 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -713,6 +713,7 @@ static void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) static struct rpc_xprt_ops xprt_rdma_procs = { .reserve_xprt = xprt_rdma_reserve_xprt, .release_xprt = xprt_release_xprt_cong, /* sunrpc/xprt.c */ + .alloc_slot = xprt_alloc_slot, .release_request = xprt_release_rqst_cong, /* ditto */ .set_retrans_timeout = xprt_set_retrans_timeout_def, /* ditto */ .rpcbind = rpcb_getport_async, /* sunrpc/rpcb_clnt.c */ diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 400567243f84..a35b8e52e551 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2473,6 +2473,7 @@ static void bc_destroy(struct rpc_xprt *xprt) static struct rpc_xprt_ops xs_local_ops = { .reserve_xprt = xprt_reserve_xprt, .release_xprt = xs_tcp_release_xprt, + .alloc_slot = xprt_alloc_slot, .rpcbind = xs_local_rpcbind, .set_port = xs_local_set_port, .connect = xs_connect, @@ -2489,6 +2490,7 @@ static struct rpc_xprt_ops xs_udp_ops = { .set_buffer_size = xs_udp_set_buffer_size, .reserve_xprt = xprt_reserve_xprt_cong, .release_xprt = xprt_release_xprt_cong, + .alloc_slot = xprt_alloc_slot, .rpcbind = rpcb_getport_async, .set_port = xs_set_port, .connect = xs_connect, @@ -2506,6 +2508,7 @@ static struct rpc_xprt_ops xs_udp_ops = { static struct rpc_xprt_ops xs_tcp_ops = { .reserve_xprt = xprt_reserve_xprt, .release_xprt = xs_tcp_release_xprt, + .alloc_slot = xprt_lock_and_alloc_slot, .rpcbind = rpcb_getport_async, .set_port = xs_set_port, .connect = xs_connect, -- cgit v1.2.3-59-g8ed1b