From 6d8d17499810479eabd10731179c04b2ca22152f Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 18 Jan 2012 12:56:02 +0300 Subject: nfsd: don't allow zero length strings in cache_parse() There is no point in passing a zero length string here and quite a few of that cache_parse() implementations will Oops if count is zero. Signed-off-by: Dan Carpenter Cc: stable@kernel.org Signed-off-by: J. Bruce Fields --- net/sunrpc/cache.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 465df9ae1046..8c6598e0334a 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -828,6 +828,8 @@ static ssize_t cache_do_downcall(char *kaddr, const char __user *buf, { ssize_t ret; + if (count == 0) + return -EINVAL; if (copy_from_user(kaddr, buf, count)) return -EFAULT; kaddr[count] = '\0'; -- cgit v1.2.3 From 3476964dba98641716173445aade77d40cc6f27a Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 20 Jan 2012 10:48:18 +0300 Subject: nfsd: remove some unneeded checks We check for zero length strings in the caller now, so these aren't needed. Signed-off-by: Dan Carpenter Signed-off-by: J. Bruce Fields --- net/sunrpc/svcauth_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 01153ead1dba..6ab35736d88f 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -509,7 +509,7 @@ static int unix_gid_parse(struct cache_detail *cd, time_t expiry; struct unix_gid ug, *ugp; - if (mlen <= 0 || mesg[mlen-1] != '\n') + if (mesg[mlen - 1] != '\n') return -EINVAL; mesg[mlen-1] = 0; -- cgit v1.2.3 From 9f912ceb7ed1df1ed98ad2c28995dd66529a690a Mon Sep 17 00:00:00 2001 From: Stanislav Kinsbursky Date: Fri, 20 Jan 2012 16:55:39 +0400 Subject: SUNPRC: remove marking service temporary sockets with XPT_CHNGBUF This is a cleanup patch. Service temporary sockets can be TCP or RDMA only. But XPT_CHNGBUF service socket flag is checked only for UDP sockets on receive. Thus (if I don't miss something non-obvious) this bit raising for temporary sockets can be removed. Signed-off-by: Stanislav Kinsbursky Signed-off-by: J. Bruce Fields --- net/sunrpc/svcsock.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'net') diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 464570906f80..b3bb18ba350a 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1381,8 +1381,6 @@ void svc_sock_update_bufs(struct svc_serv *serv) spin_lock_bh(&serv->sv_lock); list_for_each_entry(svsk, &serv->sv_permsocks, sk_xprt.xpt_list) set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags); - list_for_each_entry(svsk, &serv->sv_tempsocks, sk_xprt.xpt_list) - set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags); spin_unlock_bh(&serv->sv_lock); } EXPORT_SYMBOL_GPL(svc_sock_update_bufs); -- cgit v1.2.3 From cec56c8ff5e28f58ff13041dca7853738ae577a1 Mon Sep 17 00:00:00 2001 From: Tom Tucker Date: Wed, 15 Feb 2012 11:30:00 -0600 Subject: svcrdma: Cleanup sparse warnings in the svcrdma module The svcrdma transport was un-marshalling requests in-place. This resulted in sparse warnings due to __beXX data containing both NBO and HBO data. The code has been restructured to do byte-swapping as the header is parsed instead of when the header is validated immediately after receipt. Also moved extern declarations for the workqueue and memory pools to the private header file. Signed-off-by: Tom Tucker Signed-off-by: J. Bruce Fields --- net/sunrpc/xprtrdma/svc_rdma.c | 1 + net/sunrpc/xprtrdma/svc_rdma_marshal.c | 66 ++++++++------------------------ net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 20 +++++----- net/sunrpc/xprtrdma/svc_rdma_sendto.c | 26 +++++++------ net/sunrpc/xprtrdma/svc_rdma_transport.c | 10 +---- net/sunrpc/xprtrdma/xprt_rdma.h | 7 ++++ 6 files changed, 50 insertions(+), 80 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 09af4fab1a45..8343737e85f4 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -47,6 +47,7 @@ #include #include #include +#include "xprt_rdma.h" #define RPCDBG_FACILITY RPCDBG_SVCXPRT diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c index 9530ef2d40dc..8d2edddf48cf 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c +++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c @@ -60,21 +60,11 @@ static u32 *decode_read_list(u32 *va, u32 *vaend) struct rpcrdma_read_chunk *ch = (struct rpcrdma_read_chunk *)va; while (ch->rc_discrim != xdr_zero) { - u64 ch_offset; - if (((unsigned long)ch + sizeof(struct rpcrdma_read_chunk)) > (unsigned long)vaend) { dprintk("svcrdma: vaend=%p, ch=%p\n", vaend, ch); return NULL; } - - ch->rc_discrim = ntohl(ch->rc_discrim); - ch->rc_position = ntohl(ch->rc_position); - ch->rc_target.rs_handle = ntohl(ch->rc_target.rs_handle); - ch->rc_target.rs_length = ntohl(ch->rc_target.rs_length); - va = (u32 *)&ch->rc_target.rs_offset; - xdr_decode_hyper(va, &ch_offset); - put_unaligned(ch_offset, (u64 *)va); ch++; } return (u32 *)&ch->rc_position; @@ -91,7 +81,7 @@ void svc_rdma_rcl_chunk_counts(struct rpcrdma_read_chunk *ch, *byte_count = 0; *ch_count = 0; for (; ch->rc_discrim != 0; ch++) { - *byte_count = *byte_count + ch->rc_target.rs_length; + *byte_count = *byte_count + ntohl(ch->rc_target.rs_length); *ch_count = *ch_count + 1; } } @@ -108,7 +98,8 @@ void svc_rdma_rcl_chunk_counts(struct rpcrdma_read_chunk *ch, */ static u32 *decode_write_list(u32 *va, u32 *vaend) { - int ch_no; + int nchunks; + struct rpcrdma_write_array *ary = (struct rpcrdma_write_array *)va; @@ -121,37 +112,24 @@ static u32 *decode_write_list(u32 *va, u32 *vaend) dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend); return NULL; } - ary->wc_discrim = ntohl(ary->wc_discrim); - ary->wc_nchunks = ntohl(ary->wc_nchunks); + nchunks = ntohl(ary->wc_nchunks); if (((unsigned long)&ary->wc_array[0] + - (sizeof(struct rpcrdma_write_chunk) * ary->wc_nchunks)) > + (sizeof(struct rpcrdma_write_chunk) * nchunks)) > (unsigned long)vaend) { dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n", - ary, ary->wc_nchunks, vaend); + ary, nchunks, vaend); return NULL; } - for (ch_no = 0; ch_no < ary->wc_nchunks; ch_no++) { - u64 ch_offset; - - ary->wc_array[ch_no].wc_target.rs_handle = - ntohl(ary->wc_array[ch_no].wc_target.rs_handle); - ary->wc_array[ch_no].wc_target.rs_length = - ntohl(ary->wc_array[ch_no].wc_target.rs_length); - va = (u32 *)&ary->wc_array[ch_no].wc_target.rs_offset; - xdr_decode_hyper(va, &ch_offset); - put_unaligned(ch_offset, (u64 *)va); - } - /* * rs_length is the 2nd 4B field in wc_target and taking its * address skips the list terminator */ - return (u32 *)&ary->wc_array[ch_no].wc_target.rs_length; + return (u32 *)&ary->wc_array[nchunks].wc_target.rs_length; } static u32 *decode_reply_array(u32 *va, u32 *vaend) { - int ch_no; + int nchunks; struct rpcrdma_write_array *ary = (struct rpcrdma_write_array *)va; @@ -164,28 +142,15 @@ static u32 *decode_reply_array(u32 *va, u32 *vaend) dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend); return NULL; } - ary->wc_discrim = ntohl(ary->wc_discrim); - ary->wc_nchunks = ntohl(ary->wc_nchunks); + nchunks = ntohl(ary->wc_nchunks); if (((unsigned long)&ary->wc_array[0] + - (sizeof(struct rpcrdma_write_chunk) * ary->wc_nchunks)) > + (sizeof(struct rpcrdma_write_chunk) * nchunks)) > (unsigned long)vaend) { dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n", - ary, ary->wc_nchunks, vaend); + ary, nchunks, vaend); return NULL; } - for (ch_no = 0; ch_no < ary->wc_nchunks; ch_no++) { - u64 ch_offset; - - ary->wc_array[ch_no].wc_target.rs_handle = - ntohl(ary->wc_array[ch_no].wc_target.rs_handle); - ary->wc_array[ch_no].wc_target.rs_length = - ntohl(ary->wc_array[ch_no].wc_target.rs_length); - va = (u32 *)&ary->wc_array[ch_no].wc_target.rs_offset; - xdr_decode_hyper(va, &ch_offset); - put_unaligned(ch_offset, (u64 *)va); - } - - return (u32 *)&ary->wc_array[ch_no]; + return (u32 *)&ary->wc_array[nchunks]; } int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req, @@ -386,13 +351,14 @@ void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *ary, void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *ary, int chunk_no, - u32 rs_handle, u64 rs_offset, + __be32 rs_handle, + __be64 rs_offset, u32 write_len) { struct rpcrdma_segment *seg = &ary->wc_array[chunk_no].wc_target; - seg->rs_handle = htonl(rs_handle); + seg->rs_handle = rs_handle; + seg->rs_offset = rs_offset; seg->rs_length = htonl(write_len); - xdr_encode_hyper((u32 *) &seg->rs_offset, rs_offset); } void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *xprt, diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index df67211c4baf..41cb63b623df 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -147,7 +147,7 @@ static int map_read_chunks(struct svcxprt_rdma *xprt, page_off = 0; ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0]; ch_no = 0; - ch_bytes = ch->rc_target.rs_length; + ch_bytes = ntohl(ch->rc_target.rs_length); 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]; @@ -183,7 +183,7 @@ static int map_read_chunks(struct svcxprt_rdma *xprt, ch_no++; ch++; chl_map->ch[ch_no].start = sge_no; - ch_bytes = ch->rc_target.rs_length; + ch_bytes = ntohl(ch->rc_target.rs_length); /* If bytes remaining account for next chunk */ if (byte_count) { head->arg.page_len += ch_bytes; @@ -281,11 +281,12 @@ static int fast_reg_read_chunks(struct svcxprt_rdma *xprt, offset = 0; ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0]; for (ch_no = 0; ch_no < ch_count; ch_no++) { + int len = ntohl(ch->rc_target.rs_length); rpl_map->sge[ch_no].iov_base = frmr->kva + offset; - rpl_map->sge[ch_no].iov_len = ch->rc_target.rs_length; + rpl_map->sge[ch_no].iov_len = len; chl_map->ch[ch_no].count = 1; chl_map->ch[ch_no].start = ch_no; - offset += ch->rc_target.rs_length; + offset += len; ch++; } @@ -316,7 +317,7 @@ static int rdma_set_ctxt_sge(struct svcxprt_rdma *xprt, for (i = 0; i < count; i++) { ctxt->sge[i].length = 0; /* in case map fails */ if (!frmr) { - BUG_ON(0 == virt_to_page(vec[i].iov_base)); + BUG_ON(!virt_to_page(vec[i].iov_base)); off = (unsigned long)vec[i].iov_base & ~PAGE_MASK; ctxt->sge[i].addr = ib_dma_map_page(xprt->sc_cm_id->device, @@ -426,6 +427,7 @@ static int rdma_read_xdr(struct svcxprt_rdma *xprt, for (ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0]; ch->rc_discrim != 0; ch++, ch_no++) { + u64 rs_offset; next_sge: ctxt = svc_rdma_get_context(xprt); ctxt->direction = DMA_FROM_DEVICE; @@ -440,10 +442,10 @@ next_sge: read_wr.opcode = IB_WR_RDMA_READ; ctxt->wr_op = read_wr.opcode; read_wr.send_flags = IB_SEND_SIGNALED; - read_wr.wr.rdma.rkey = ch->rc_target.rs_handle; - read_wr.wr.rdma.remote_addr = - get_unaligned(&(ch->rc_target.rs_offset)) + - sgl_offset; + read_wr.wr.rdma.rkey = ntohl(ch->rc_target.rs_handle); + xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset, + &rs_offset); + read_wr.wr.rdma.remote_addr = rs_offset + sgl_offset; read_wr.sg_list = ctxt->sge; read_wr.num_sge = rdma_read_max_sge(xprt, chl_map->ch[ch_no].count); diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 249a835b703f..42eb7ba0b903 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -409,21 +409,21 @@ static int send_write_chunks(struct svcxprt_rdma *xprt, u64 rs_offset; arg_ch = &arg_ary->wc_array[chunk_no].wc_target; - write_len = min(xfer_len, arg_ch->rs_length); + write_len = min(xfer_len, ntohl(arg_ch->rs_length)); /* Prepare the response chunk given the length actually * written */ - rs_offset = get_unaligned(&(arg_ch->rs_offset)); + xdr_decode_hyper((__be32 *)&arg_ch->rs_offset, &rs_offset); svc_rdma_xdr_encode_array_chunk(res_ary, chunk_no, - arg_ch->rs_handle, - rs_offset, - write_len); + arg_ch->rs_handle, + arg_ch->rs_offset, + write_len); chunk_off = 0; while (write_len) { int this_write; this_write = min(write_len, max_write); ret = send_write(xprt, rqstp, - arg_ch->rs_handle, + ntohl(arg_ch->rs_handle), rs_offset + chunk_off, xdr_off, this_write, @@ -457,6 +457,7 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt, u32 xdr_off; int chunk_no; int chunk_off; + int nchunks; struct rpcrdma_segment *ch; struct rpcrdma_write_array *arg_ary; struct rpcrdma_write_array *res_ary; @@ -476,26 +477,27 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt, max_write = xprt->sc_max_sge * PAGE_SIZE; /* xdr offset starts at RPC message */ + nchunks = ntohl(arg_ary->wc_nchunks); for (xdr_off = 0, chunk_no = 0; - xfer_len && chunk_no < arg_ary->wc_nchunks; + xfer_len && chunk_no < nchunks; chunk_no++) { u64 rs_offset; ch = &arg_ary->wc_array[chunk_no].wc_target; - write_len = min(xfer_len, ch->rs_length); + write_len = min(xfer_len, htonl(ch->rs_length)); /* Prepare the reply chunk given the length actually * written */ - rs_offset = get_unaligned(&(ch->rs_offset)); + xdr_decode_hyper((__be32 *)&ch->rs_offset, &rs_offset); svc_rdma_xdr_encode_array_chunk(res_ary, chunk_no, - ch->rs_handle, rs_offset, - write_len); + ch->rs_handle, ch->rs_offset, + write_len); chunk_off = 0; while (write_len) { int this_write; this_write = min(write_len, max_write); ret = send_write(xprt, rqstp, - ch->rs_handle, + ntohl(ch->rs_handle), rs_offset + chunk_off, xdr_off, this_write, diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 894cb42db91d..73b428bef598 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -51,6 +51,7 @@ #include #include #include +#include "xprt_rdma.h" #define RPCDBG_FACILITY RPCDBG_SVCXPRT @@ -90,12 +91,6 @@ struct svc_xprt_class svc_rdma_class = { .xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP, }; -/* WR context cache. Created in svc_rdma.c */ -extern struct kmem_cache *svc_rdma_ctxt_cachep; - -/* Workqueue created in svc_rdma.c */ -extern struct workqueue_struct *svc_rdma_wq; - struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) { struct svc_rdma_op_ctxt *ctxt; @@ -150,9 +145,6 @@ 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 diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 08c5d5a128fc..9a66c95b5837 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -343,4 +343,11 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *); */ int rpcrdma_marshal_req(struct rpc_rqst *); +/* Temporary NFS request map cache. Created in svc_rdma.c */ +extern struct kmem_cache *svc_rdma_map_cachep; +/* WR context cache. Created in svc_rdma.c */ +extern struct kmem_cache *svc_rdma_ctxt_cachep; +/* Workqueue created in svc_rdma.c */ +extern struct workqueue_struct *svc_rdma_wq; + #endif /* _LINUX_SUNRPC_XPRT_RDMA_H */ -- cgit v1.2.3 From da88cea1200b9df65a7811a3920aa5a4be7dab9f Mon Sep 17 00:00:00 2001 From: "H. J. Lu" Date: Fri, 10 Feb 2012 14:12:15 -0800 Subject: compat: Use COMPAT_USE_64BIT_TIME in the Bluetooth subsystem Enable the Bluetooth subsystem to be used with a compat ABI with 64-bit time. Signed-off-by: H. Peter Anvin Cc: Marcel Holtmann Cc: Gustavo F. Padovan Cc: David S. Miller --- net/bluetooth/hci_sock.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 0dcc96266779..b2eb2b93580f 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -418,7 +418,8 @@ static inline void hci_sock_cmsg(struct sock *sk, struct msghdr *msg, struct sk_ data = &tv; len = sizeof(tv); #ifdef CONFIG_COMPAT - if (msg->msg_flags & MSG_CMSG_COMPAT) { + if (!COMPAT_USE_64BIT_TIME && + (msg->msg_flags & MSG_CMSG_COMPAT)) { ctv.tv_sec = tv.tv_sec; ctv.tv_usec = tv.tv_usec; data = &ctv; -- cgit v1.2.3 From ee4fa23c4bfcc635d077a9633d405610de45bc70 Mon Sep 17 00:00:00 2001 From: "H. J. Lu" Date: Sun, 19 Feb 2012 17:50:46 -0800 Subject: compat: Use COMPAT_USE_64BIT_TIME in net/compat.c Handle 64-bit time structures in the networking core compat code. Signed-off-by: H. Peter Anvin Cc: David S. Miller --- net/compat.c | 65 +++++++++++++++++++++++++++++++++++++----------------------- 1 file changed, 40 insertions(+), 25 deletions(-) (limited to 'net') diff --git a/net/compat.c b/net/compat.c index 6def90e0a112..73bf0e06f3d7 100644 --- a/net/compat.c +++ b/net/compat.c @@ -219,8 +219,6 @@ Efault: int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *data) { - struct compat_timeval ctv; - struct compat_timespec cts[3]; struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *) kmsg->msg_control; struct compat_cmsghdr cmhdr; int cmlen; @@ -230,24 +228,28 @@ int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *dat return 0; /* XXX: return error? check spec. */ } - if (level == SOL_SOCKET && type == SCM_TIMESTAMP) { - struct timeval *tv = (struct timeval *)data; - ctv.tv_sec = tv->tv_sec; - ctv.tv_usec = tv->tv_usec; - data = &ctv; - len = sizeof(ctv); - } - if (level == SOL_SOCKET && - (type == SCM_TIMESTAMPNS || type == SCM_TIMESTAMPING)) { - int count = type == SCM_TIMESTAMPNS ? 1 : 3; - int i; - struct timespec *ts = (struct timespec *)data; - for (i = 0; i < count; i++) { - cts[i].tv_sec = ts[i].tv_sec; - cts[i].tv_nsec = ts[i].tv_nsec; + if (!COMPAT_USE_64BIT_TIME) { + struct compat_timeval ctv; + struct compat_timespec cts[3]; + if (level == SOL_SOCKET && type == SCM_TIMESTAMP) { + struct timeval *tv = (struct timeval *)data; + ctv.tv_sec = tv->tv_sec; + ctv.tv_usec = tv->tv_usec; + data = &ctv; + len = sizeof(ctv); + } + if (level == SOL_SOCKET && + (type == SCM_TIMESTAMPNS || type == SCM_TIMESTAMPING)) { + int count = type == SCM_TIMESTAMPNS ? 1 : 3; + int i; + struct timespec *ts = (struct timespec *)data; + for (i = 0; i < count; i++) { + cts[i].tv_sec = ts[i].tv_sec; + cts[i].tv_nsec = ts[i].tv_nsec; + } + data = &cts; + len = sizeof(cts[0]) * count; } - data = &cts; - len = sizeof(cts[0]) * count; } cmlen = CMSG_COMPAT_LEN(len); @@ -454,11 +456,15 @@ static int compat_sock_getsockopt(struct socket *sock, int level, int optname, int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) { - struct compat_timeval __user *ctv = - (struct compat_timeval __user *) userstamp; - int err = -ENOENT; + struct compat_timeval __user *ctv; + int err; struct timeval tv; + if (COMPAT_USE_64BIT_TIME) + return sock_get_timestamp(sk, userstamp); + + ctv = (struct compat_timeval __user *) userstamp; + err = -ENOENT; if (!sock_flag(sk, SOCK_TIMESTAMP)) sock_enable_timestamp(sk, SOCK_TIMESTAMP); tv = ktime_to_timeval(sk->sk_stamp); @@ -478,11 +484,15 @@ EXPORT_SYMBOL(compat_sock_get_timestamp); int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp) { - struct compat_timespec __user *ctv = - (struct compat_timespec __user *) userstamp; - int err = -ENOENT; + struct compat_timespec __user *ctv; + int err; struct timespec ts; + if (COMPAT_USE_64BIT_TIME) + return sock_get_timestampns (sk, userstamp); + + ctv = (struct compat_timespec __user *) userstamp; + err = -ENOENT; if (!sock_flag(sk, SOCK_TIMESTAMP)) sock_enable_timestamp(sk, SOCK_TIMESTAMP); ts = ktime_to_timespec(sk->sk_stamp); @@ -767,6 +777,11 @@ asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, int datagrams; struct timespec ktspec; + if (COMPAT_USE_64BIT_TIME) + return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, + flags | MSG_CMSG_COMPAT, + (struct timespec *) timeout); + if (timeout == NULL) return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT, NULL); -- cgit v1.2.3 From 644595f89620ba8446cc555be336d24a34464950 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Sun, 19 Feb 2012 17:51:59 -0800 Subject: compat: Handle COMPAT_USE_64BIT_TIME in net/socket.c Use helper functions aware of COMPAT_USE_64BIT_TIME to write struct timeval and struct timespec to userspace in net/socket.c. Signed-off-by: H. Peter Anvin --- net/socket.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) (limited to 'net') diff --git a/net/socket.c b/net/socket.c index 28a96af484b4..5325d4c797c9 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2600,7 +2600,7 @@ void socket_seq_show(struct seq_file *seq) #ifdef CONFIG_COMPAT static int do_siocgstamp(struct net *net, struct socket *sock, - unsigned int cmd, struct compat_timeval __user *up) + unsigned int cmd, void __user *up) { mm_segment_t old_fs = get_fs(); struct timeval ktv; @@ -2609,15 +2609,14 @@ static int do_siocgstamp(struct net *net, struct socket *sock, set_fs(KERNEL_DS); err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv); set_fs(old_fs); - if (!err) { - err = put_user(ktv.tv_sec, &up->tv_sec); - err |= __put_user(ktv.tv_usec, &up->tv_usec); - } + if (!err) + err = compat_put_timeval(up, &ktv); + return err; } static int do_siocgstampns(struct net *net, struct socket *sock, - unsigned int cmd, struct compat_timespec __user *up) + unsigned int cmd, void __user *up) { mm_segment_t old_fs = get_fs(); struct timespec kts; @@ -2626,10 +2625,9 @@ static int do_siocgstampns(struct net *net, struct socket *sock, set_fs(KERNEL_DS); err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts); set_fs(old_fs); - if (!err) { - err = put_user(kts.tv_sec, &up->tv_sec); - err |= __put_user(kts.tv_nsec, &up->tv_nsec); - } + if (!err) + err = compat_put_timespec(up, &kts); + return err; } -- cgit v1.2.3 From a314f2748e76c866222a18e639c640d584d277fb Mon Sep 17 00:00:00 2001 From: Jim Garlick Date: Wed, 1 Feb 2012 12:48:53 -0800 Subject: net/9p: don't allow Tflush to be interrupted When a signal is received while sending a Tflush, the client, which has recursed into p9_client_rpc() while sending another request, should wait for Rflush as long as the transport is still up. Signed-off-by: Jim Garlick Signed-off-by: Eric Van Hensbergen --- net/9p/client.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'net') diff --git a/net/9p/client.c b/net/9p/client.c index 776618cd2be5..6efbb334c3ad 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -740,10 +740,18 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...) c->status = Disconnected; goto reterr; } +again: /* Wait for the response */ err = wait_event_interruptible(*req->wq, req->status >= REQ_STATUS_RCVD); + if ((err == -ERESTARTSYS) && (c->status == Connected) + && (type == P9_TFLUSH)) { + sigpending = 1; + clear_thread_flag(TIF_SIGPENDING); + goto again; + } + if (req->status == REQ_STATUS_ERROR) { p9_debug(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err); err = req->t_err; -- cgit v1.2.3 From 208f3c28aab706fca2bc1bae7091da8a99c5e322 Mon Sep 17 00:00:00 2001 From: Jim Garlick Date: Sun, 26 Feb 2012 14:49:57 -0600 Subject: net/9p: handle flushed Tclunk/Tremove When a Tclunk or Tremove request is flushed, the fid is not freed on the server. p9_client_clunk() should retry once on interrupt, then if interrupted again, leak the fid for the duration of the connection. p9_client_remove() should call p9_client_clunk() on interrupt instead of unconditionally destroying the fid. Signed-off-by: Jim Garlick Signed-off-by: Eric Van Hensbergen --- net/9p/client.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/9p/client.c b/net/9p/client.c index 6efbb334c3ad..b23a17c431c8 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -1428,6 +1428,7 @@ int p9_client_clunk(struct p9_fid *fid) int err; struct p9_client *clnt; struct p9_req_t *req; + int retries = 0; if (!fid) { pr_warn("%s (%d): Trying to clunk with NULL fid\n", @@ -1436,7 +1437,9 @@ int p9_client_clunk(struct p9_fid *fid) return 0; } - p9_debug(P9_DEBUG_9P, ">>> TCLUNK fid %d\n", fid->fid); +again: + p9_debug(P9_DEBUG_9P, ">>> TCLUNK fid %d (try %d)\n", fid->fid, + retries); err = 0; clnt = fid->clnt; @@ -1452,8 +1455,14 @@ int p9_client_clunk(struct p9_fid *fid) error: /* * Fid is not valid even after a failed clunk + * If interrupted, retry once then give up and + * leak fid until umount. */ - p9_fid_destroy(fid); + if (err == -ERESTARTSYS) { + if (retries++ == 0) + goto again; + } else + p9_fid_destroy(fid); return err; } EXPORT_SYMBOL(p9_client_clunk); @@ -1478,7 +1487,10 @@ int p9_client_remove(struct p9_fid *fid) p9_free_req(clnt, req); error: - p9_fid_destroy(fid); + if (err == -ERESTARTSYS) + p9_client_clunk(fid); + else + p9_fid_destroy(fid); return err; } EXPORT_SYMBOL(p9_client_remove); -- cgit v1.2.3 From 182fac2689b769a96e7fc9defcd560c5cca92b1e Mon Sep 17 00:00:00 2001 From: Jim Schutt Date: Wed, 29 Feb 2012 08:30:58 -0700 Subject: net/ceph: Only clear SOCK_NOSPACE when there is sufficient space in the socket buffer The Ceph messenger would sometimes queue multiple work items to write data to a socket when the socket buffer was full. Fix this problem by making ceph_write_space() use SOCK_NOSPACE in the same way that net/core/stream.c:sk_stream_write_space() does, i.e., clearing it only when sufficient space is available in the socket buffer. Signed-off-by: Jim Schutt Reviewed-by: Alex Elder --- net/ceph/messenger.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index ad5b70801f37..d11f91b05452 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -143,16 +143,22 @@ static void ceph_write_space(struct sock *sk) struct ceph_connection *con = (struct ceph_connection *)sk->sk_user_data; - /* only queue to workqueue if there is data we want to write. */ + /* only queue to workqueue if there is data we want to write, + * and there is sufficient space in the socket buffer to accept + * more data. clear SOCK_NOSPACE so that ceph_write_space() + * doesn't get called again until try_write() fills the socket + * buffer. See net/ipv4/tcp_input.c:tcp_check_space() + * and net/core/stream.c:sk_stream_write_space(). + */ if (test_bit(WRITE_PENDING, &con->state)) { - dout("ceph_write_space %p queueing write work\n", con); - queue_con(con); + if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) { + dout("ceph_write_space %p queueing write work\n", con); + clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + queue_con(con); + } } else { dout("ceph_write_space %p nothing to write\n", con); } - - /* since we have our own write_space, clear the SOCK_NOSPACE flag */ - clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); } /* socket's state has changed */ -- cgit v1.2.3 From 64486697771cbe219fffcb5c8e2ed9ca4fdf086c Mon Sep 17 00:00:00 2001 From: Xi Wang Date: Thu, 16 Feb 2012 11:55:48 -0500 Subject: libceph: fix overflow check in crush_decode() The existing overflow check (n > ULONG_MAX / b) didn't work, because n = ULONG_MAX / b would both bypass the check and still overflow the allocation size a + n * b. The correct check should be (n > (ULONG_MAX - a) / b). Signed-off-by: Xi Wang Signed-off-by: Sage Weil --- net/ceph/osdmap.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index fd863fe76934..29ad46ec9dcf 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -283,7 +283,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end) ceph_decode_32_safe(p, end, yes, bad); #if BITS_PER_LONG == 32 err = -EINVAL; - if (yes > ULONG_MAX / sizeof(struct crush_rule_step)) + if (yes > (ULONG_MAX - sizeof(*r)) + / sizeof(struct crush_rule_step)) goto bad; #endif r = c->rules[i] = kmalloc(sizeof(*r) + -- cgit v1.2.3 From 5766651971e81298732466c9aa462ff47898ba37 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 23 Jan 2012 15:49:27 -0600 Subject: ceph: use a shared zero page rather than one per messenger Each messenger allocates a page to be used when writing zeroes out in the event of error or other abnormal condition. Instead, use the kernel ZERO_PAGE() for that purpose. Signed-off-by: Alex Elder Signed-off-by: Sage Weil --- net/ceph/messenger.c | 43 +++++++++++++++++++++++++++++-------------- 1 file changed, 29 insertions(+), 14 deletions(-) (limited to 'net') diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index d11f91b05452..738356255e0b 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -52,6 +52,9 @@ static char addr_str[MAX_ADDR_STR][MAX_ADDR_STR_LEN]; static DEFINE_SPINLOCK(addr_str_lock); static int last_addr_str; +static struct page *zero_page; /* used in certain error cases */ +static void *zero_page_address; /* kernel virtual addr of zero_page */ + const char *ceph_pr_addr(const struct sockaddr_storage *ss) { int i; @@ -99,18 +102,41 @@ struct workqueue_struct *ceph_msgr_wq; int ceph_msgr_init(void) { + BUG_ON(zero_page != NULL); + zero_page = ZERO_PAGE(0); + page_cache_get(zero_page); + + BUG_ON(zero_page_address != NULL); + zero_page_address = kmap(zero_page); + ceph_msgr_wq = alloc_workqueue("ceph-msgr", WQ_NON_REENTRANT, 0); if (!ceph_msgr_wq) { pr_err("msgr_init failed to create workqueue\n"); + + zero_page_address = NULL; + kunmap(zero_page); + page_cache_release(zero_page); + zero_page = NULL; + return -ENOMEM; } + return 0; } EXPORT_SYMBOL(ceph_msgr_init); void ceph_msgr_exit(void) { + BUG_ON(ceph_msgr_wq == NULL); destroy_workqueue(ceph_msgr_wq); + + BUG_ON(zero_page_address == NULL); + zero_page_address = NULL; + + BUG_ON(zero_page == NULL); + kunmap(zero_page); + page_cache_release(zero_page); + zero_page = NULL; } EXPORT_SYMBOL(ceph_msgr_exit); @@ -841,9 +867,9 @@ static int write_partial_msg_pages(struct ceph_connection *con) max_write = bv->bv_len; #endif } else { - page = con->msgr->zero_page; + page = zero_page; if (crc) - kaddr = page_address(con->msgr->zero_page); + kaddr = zero_page_address; } len = min_t(int, max_write - con->out_msg_pos.page_pos, total_max_write); @@ -914,7 +940,7 @@ static int write_partial_skip(struct ceph_connection *con) while (con->out_skip > 0) { struct kvec iov = { - .iov_base = page_address(con->msgr->zero_page), + .iov_base = zero_page_address, .iov_len = min(con->out_skip, (int)PAGE_CACHE_SIZE) }; @@ -2222,15 +2248,6 @@ struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr, spin_lock_init(&msgr->global_seq_lock); - /* the zero page is needed if a request is "canceled" while the message - * is being written over the socket */ - msgr->zero_page = __page_cache_alloc(GFP_KERNEL | __GFP_ZERO); - if (!msgr->zero_page) { - kfree(msgr); - return ERR_PTR(-ENOMEM); - } - kmap(msgr->zero_page); - if (myaddr) msgr->inst.addr = *myaddr; @@ -2247,8 +2264,6 @@ EXPORT_SYMBOL(ceph_messenger_create); void ceph_messenger_destroy(struct ceph_messenger *msgr) { dout("destroy %p\n", msgr); - kunmap(msgr->zero_page); - __free_page(msgr->zero_page); kfree(msgr); dout("destroyed messenger %p\n", msgr); } -- cgit v1.2.3 From a5bc3129a296fd4663c3ef0be5575e82453739dd Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 23 Jan 2012 15:49:27 -0600 Subject: ceph: make use of "else" where appropriate Rearrange ceph_tcp_connect() a bit, making use of "else" rather than re-testing a value with consecutive "if" statements. Don't record a connection's socket pointer unless the connect operation is successful. Signed-off-by: Alex Elder Signed-off-by: Sage Weil --- net/ceph/messenger.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'net') diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 738356255e0b..b5536e4e39a1 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -251,7 +251,6 @@ static struct socket *ceph_tcp_connect(struct ceph_connection *con) IPPROTO_TCP, &sock); if (ret) return ERR_PTR(ret); - con->sock = sock; sock->sk->sk_allocation = GFP_NOFS; #ifdef CONFIG_LOCKDEP @@ -268,18 +267,16 @@ static struct socket *ceph_tcp_connect(struct ceph_connection *con) dout("connect %s EINPROGRESS sk_state = %u\n", ceph_pr_addr(&con->peer_addr.in_addr), sock->sk->sk_state); - ret = 0; - } - if (ret < 0) { + } else if (ret < 0) { pr_err("connect %s error %d\n", ceph_pr_addr(&con->peer_addr.in_addr), ret); sock_release(sock); - con->sock = NULL; con->error_msg = "connect error"; - } - if (ret < 0) return ERR_PTR(ret); + } + con->sock = sock; + return sock; } -- cgit v1.2.3 From f64a93172b97dcfcfa68f595652220653562f605 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 23 Jan 2012 15:49:27 -0600 Subject: ceph: kill addr_str_lock spinlock; use atomic instead A spinlock is used to protect a value used for selecting an array index for a string used for formatting a socket address for human consumption. The index is reset to 0 if it ever reaches the maximum index value. Instead, use an ever-increasing atomic variable as a sequence number, and compute the array index by masking off all but the sequence number's lowest bits. Make the number of entries in the array a power of two to allow the use of such a mask (to avoid jumps in the index value when the sequence number wraps). The length of these strings is somewhat arbitrarily set at 60 bytes. The worst-case length of a string produced is 54 bytes, for an IPv6 address that can't be shortened, e.g.: [1234:5678:9abc:def0:1111:2222:123.234.210.100]:32767 Change it so we arbitrarily use 64 bytes instead; if nothing else it will make the array of these line up better in hex dumps. Rename a few things to reinforce the distinction between the number of strings in the array and the length of individual strings. Signed-off-by: Alex Elder Signed-off-by: Sage Weil --- net/ceph/messenger.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) (limited to 'net') diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index b5536e4e39a1..e86bb3f14859 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -44,13 +44,16 @@ static void con_work(struct work_struct *); static void ceph_fault(struct ceph_connection *con); /* - * nicely render a sockaddr as a string. + * Nicely render a sockaddr as a string. An array of formatted + * strings is used, to approximate reentrancy. */ -#define MAX_ADDR_STR 20 -#define MAX_ADDR_STR_LEN 60 -static char addr_str[MAX_ADDR_STR][MAX_ADDR_STR_LEN]; -static DEFINE_SPINLOCK(addr_str_lock); -static int last_addr_str; +#define ADDR_STR_COUNT_LOG 5 /* log2(# address strings in array) */ +#define ADDR_STR_COUNT (1 << ADDR_STR_COUNT_LOG) +#define ADDR_STR_COUNT_MASK (ADDR_STR_COUNT - 1) +#define MAX_ADDR_STR_LEN 64 /* 54 is enough */ + +static char addr_str[ADDR_STR_COUNT][MAX_ADDR_STR_LEN]; +static atomic_t addr_str_seq = ATOMIC_INIT(0); static struct page *zero_page; /* used in certain error cases */ static void *zero_page_address; /* kernel virtual addr of zero_page */ @@ -62,11 +65,7 @@ const char *ceph_pr_addr(const struct sockaddr_storage *ss) struct sockaddr_in *in4 = (void *)ss; struct sockaddr_in6 *in6 = (void *)ss; - spin_lock(&addr_str_lock); - i = last_addr_str++; - if (last_addr_str == MAX_ADDR_STR) - last_addr_str = 0; - spin_unlock(&addr_str_lock); + i = atomic_inc_return(&addr_str_seq) & ADDR_STR_COUNT_MASK; s = addr_str[i]; switch (ss->ss_family) { -- cgit v1.2.3 From bd406145129e8724cc71b65ff2a788dbd4d60c50 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 23 Jan 2012 15:49:27 -0600 Subject: ceph: eliminate some needless casts This eliminates type casts in some places where they are not required. Signed-off-by: Alex Elder Signed-off-by: Sage Weil --- net/ceph/messenger.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) (limited to 'net') diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index e86bb3f14859..09a412ba4b70 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -70,13 +70,13 @@ const char *ceph_pr_addr(const struct sockaddr_storage *ss) switch (ss->ss_family) { case AF_INET: - snprintf(s, MAX_ADDR_STR_LEN, "%pI4:%u", &in4->sin_addr, - (unsigned int)ntohs(in4->sin_port)); + snprintf(s, MAX_ADDR_STR_LEN, "%pI4:%hu", &in4->sin_addr, + ntohs(in4->sin_port)); break; case AF_INET6: - snprintf(s, MAX_ADDR_STR_LEN, "[%pI6c]:%u", &in6->sin6_addr, - (unsigned int)ntohs(in6->sin6_port)); + snprintf(s, MAX_ADDR_STR_LEN, "[%pI6c]:%hu", &in6->sin6_addr, + ntohs(in6->sin6_port)); break; default: @@ -153,8 +153,8 @@ EXPORT_SYMBOL(ceph_msgr_flush); /* data available on socket, or listen socket received a connect */ static void ceph_data_ready(struct sock *sk, int count_unused) { - struct ceph_connection *con = - (struct ceph_connection *)sk->sk_user_data; + struct ceph_connection *con = sk->sk_user_data; + if (sk->sk_state != TCP_CLOSE_WAIT) { dout("ceph_data_ready on %p state = %lu, queueing work\n", con, con->state); @@ -189,8 +189,7 @@ static void ceph_write_space(struct sock *sk) /* socket's state has changed */ static void ceph_state_change(struct sock *sk) { - struct ceph_connection *con = - (struct ceph_connection *)sk->sk_user_data; + struct ceph_connection *con = sk->sk_user_data; dout("ceph_state_change %p state = %lu sk_state = %u\n", con, con->state, sk->sk_state); @@ -225,7 +224,7 @@ static void set_sock_callbacks(struct socket *sock, struct ceph_connection *con) { struct sock *sk = sock->sk; - sk->sk_user_data = (void *)con; + sk->sk_user_data = con; sk->sk_data_ready = ceph_data_ready; sk->sk_write_space = ceph_write_space; sk->sk_state_change = ceph_state_change; @@ -552,7 +551,7 @@ static void prepare_write_message(struct ceph_connection *con) /* fill in crc (except data pages), footer */ con->out_msg->hdr.crc = - cpu_to_le32(crc32c(0, (void *)&m->hdr, + cpu_to_le32(crc32c(0, &m->hdr, sizeof(m->hdr) - sizeof(m->hdr.crc))); con->out_msg->footer.flags = CEPH_MSG_FOOTER_COMPLETE; con->out_msg->footer.front_crc = @@ -1647,7 +1646,7 @@ static int read_partial_message(struct ceph_connection *con) return ret; con->in_base_pos += ret; if (con->in_base_pos == sizeof(con->in_hdr)) { - u32 crc = crc32c(0, (void *)&con->in_hdr, + u32 crc = crc32c(0, &con->in_hdr, sizeof(con->in_hdr) - sizeof(con->in_hdr.crc)); if (crc != le32_to_cpu(con->in_hdr.crc)) { pr_err("read_partial_message bad hdr " -- cgit v1.2.3 From 99f0f3b2c4be15784bb4ede33b5f2c3f7861dba7 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 23 Jan 2012 15:49:27 -0600 Subject: ceph: eliminate some abusive casts This fixes some spots where a type cast to (void *) was used as as a universal type hiding mechanism. Instead, properly cast the type to the intended target type. Signed-off-by: Alex Elder Signed-off-by: Sage Weil --- net/ceph/messenger.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 09a412ba4b70..3917847ad8e5 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -62,8 +62,8 @@ const char *ceph_pr_addr(const struct sockaddr_storage *ss) { int i; char *s; - struct sockaddr_in *in4 = (void *)ss; - struct sockaddr_in6 *in6 = (void *)ss; + struct sockaddr_in *in4 = (struct sockaddr_in *) ss; + struct sockaddr_in6 *in6 = (struct sockaddr_in6 *) ss; i = atomic_inc_return(&addr_str_seq) & ADDR_STR_COUNT_MASK; s = addr_str[i]; @@ -1112,8 +1112,8 @@ static void addr_set_port(struct sockaddr_storage *ss, int p) static int ceph_pton(const char *str, size_t len, struct sockaddr_storage *ss, char delim, const char **ipend) { - struct sockaddr_in *in4 = (void *)ss; - struct sockaddr_in6 *in6 = (void *)ss; + struct sockaddr_in *in4 = (struct sockaddr_in *) ss; + struct sockaddr_in6 *in6 = (struct sockaddr_in6 *) ss; memset(ss, 0, sizeof(*ss)); -- cgit v1.2.3 From ee57741c5209154b8ef124bcaa2496da1b69a988 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 24 Jan 2012 10:08:36 -0600 Subject: rbd: make ceph_parse_options() return a pointer ceph_parse_options() takes the address of a pointer as an argument and uses it to return the address of an allocated structure if successful. With this interface is not evident at call sites that the pointer is always initialized. Change the interface to return the address instead (or a pointer-coded error code) to make the validity of the returned pointer obvious. Signed-off-by: Alex Elder Signed-off-by: Sage Weil --- net/ceph/ceph_common.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 761ad9d6cc3b..621c3221b393 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -277,10 +277,11 @@ out: return err; } -int ceph_parse_options(struct ceph_options **popt, char *options, - const char *dev_name, const char *dev_name_end, - int (*parse_extra_token)(char *c, void *private), - void *private) +struct ceph_options * +ceph_parse_options(char *options, const char *dev_name, + const char *dev_name_end, + int (*parse_extra_token)(char *c, void *private), + void *private) { struct ceph_options *opt; const char *c; @@ -289,7 +290,7 @@ int ceph_parse_options(struct ceph_options **popt, char *options, opt = kzalloc(sizeof(*opt), GFP_KERNEL); if (!opt) - return err; + return ERR_PTR(-ENOMEM); opt->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*opt->mon_addr), GFP_KERNEL); if (!opt->mon_addr) @@ -412,12 +413,11 @@ int ceph_parse_options(struct ceph_options **popt, char *options, } /* success */ - *popt = opt; - return 0; + return opt; out: ceph_destroy_options(opt); - return err; + return ERR_PTR(err); } EXPORT_SYMBOL(ceph_parse_options); -- cgit v1.2.3 From 963be4d7709f84d865f76d12d5b0ec7edad1c498 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 14 Feb 2012 14:05:33 -0600 Subject: libceph: move prepare_write_banner() One of the arguments to prepare_write_connect() indicates whether it is being called immediately after a call to prepare_write_banner(). Move the prepare_write_banner() call inside prepare_write_connect(), and reinterpret (and rename) the "after_banner" argument so it indicates that prepare_write_connect() should *make* the call rather than should know it has already been made. This was split out from the next patch to highlight this change in logic. Signed-off-by: Alex Elder Signed-off-by: Sage Weil --- net/ceph/messenger.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 3917847ad8e5..0665945b6468 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -676,7 +676,7 @@ static void prepare_write_banner(struct ceph_messenger *msgr, static int prepare_write_connect(struct ceph_messenger *msgr, struct ceph_connection *con, - int after_banner) + int include_banner) { unsigned global_seq = get_global_seq(con->msgr, 0); int proto; @@ -705,7 +705,9 @@ static int prepare_write_connect(struct ceph_messenger *msgr, con->out_connect.protocol_version = cpu_to_le32(proto); con->out_connect.flags = 0; - if (!after_banner) { + if (include_banner) + prepare_write_banner(msgr, con); + else { con->out_kvec_left = 0; con->out_kvec_bytes = 0; } @@ -1846,7 +1848,6 @@ more: /* open the socket first? */ if (con->sock == NULL) { - prepare_write_banner(msgr, con); prepare_write_connect(msgr, con, 1); prepare_read_banner(con); set_bit(CONNECTING, &con->state); -- cgit v1.2.3 From 859eb7994876f26fd9f52d9589fbcab8e2fe8069 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 14 Feb 2012 14:05:33 -0600 Subject: libceph: encapsulate connection kvec operations Encapsulate the operation of adding a new chunk of data to the next open slot in a ceph_connection's out_kvec array. Also add a "reset" operation to make subsequent add operations start at the beginning of the array again. Use these routines throughout, avoiding duplicate code and ensuring all calls are handled consistently. Signed-off-by: Alex Elder Signed-off-by: Sage Weil --- net/ceph/messenger.c | 117 ++++++++++++++++++++++++--------------------------- 1 file changed, 56 insertions(+), 61 deletions(-) (limited to 'net') diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 0665945b6468..04d2b975ab0c 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -469,14 +469,35 @@ static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt) return ret; } +static void ceph_con_out_kvec_reset(struct ceph_connection *con) +{ + con->out_kvec_left = 0; + con->out_kvec_bytes = 0; + con->out_kvec_cur = &con->out_kvec[0]; +} + +static void ceph_con_out_kvec_add(struct ceph_connection *con, + size_t size, void *data) +{ + int index; + + index = con->out_kvec_left; + BUG_ON(index >= ARRAY_SIZE(con->out_kvec)); + + con->out_kvec[index].iov_len = size; + con->out_kvec[index].iov_base = data; + con->out_kvec_left++; + con->out_kvec_bytes += size; +} /* * Prepare footer for currently outgoing message, and finish things * off. Assumes out_kvec* are already valid.. we just add on to the end. */ -static void prepare_write_message_footer(struct ceph_connection *con, int v) +static void prepare_write_message_footer(struct ceph_connection *con) { struct ceph_msg *m = con->out_msg; + int v = con->out_kvec_left; dout("prepare_write_message_footer %p\n", con); con->out_kvec_is_msg = true; @@ -494,9 +515,8 @@ static void prepare_write_message_footer(struct ceph_connection *con, int v) static void prepare_write_message(struct ceph_connection *con) { struct ceph_msg *m; - int v = 0; - con->out_kvec_bytes = 0; + ceph_con_out_kvec_reset(con); con->out_kvec_is_msg = true; con->out_msg_done = false; @@ -504,16 +524,13 @@ static void prepare_write_message(struct ceph_connection *con) * TCP packet that's a good thing. */ if (con->in_seq > con->in_seq_acked) { con->in_seq_acked = con->in_seq; - con->out_kvec[v].iov_base = &tag_ack; - con->out_kvec[v++].iov_len = 1; + ceph_con_out_kvec_add(con, sizeof (tag_ack), &tag_ack); con->out_temp_ack = cpu_to_le64(con->in_seq_acked); - con->out_kvec[v].iov_base = &con->out_temp_ack; - con->out_kvec[v++].iov_len = sizeof(con->out_temp_ack); - con->out_kvec_bytes = 1 + sizeof(con->out_temp_ack); + ceph_con_out_kvec_add(con, sizeof (con->out_temp_ack), + &con->out_temp_ack); } - m = list_first_entry(&con->out_queue, - struct ceph_msg, list_head); + m = list_first_entry(&con->out_queue, struct ceph_msg, list_head); con->out_msg = m; /* put message on sent list */ @@ -537,17 +554,13 @@ static void prepare_write_message(struct ceph_connection *con) BUG_ON(le32_to_cpu(m->hdr.front_len) != m->front.iov_len); /* tag + hdr + front + middle */ - con->out_kvec[v].iov_base = &tag_msg; - con->out_kvec[v++].iov_len = 1; - con->out_kvec[v].iov_base = &m->hdr; - con->out_kvec[v++].iov_len = sizeof(m->hdr); - con->out_kvec[v++] = m->front; + ceph_con_out_kvec_add(con, sizeof (tag_msg), &tag_msg); + ceph_con_out_kvec_add(con, sizeof (m->hdr), &m->hdr); + ceph_con_out_kvec_add(con, m->front.iov_len, m->front.iov_base); + if (m->middle) - con->out_kvec[v++] = m->middle->vec; - con->out_kvec_left = v; - con->out_kvec_bytes += 1 + sizeof(m->hdr) + m->front.iov_len + - (m->middle ? m->middle->vec.iov_len : 0); - con->out_kvec_cur = con->out_kvec; + ceph_con_out_kvec_add(con, m->middle->vec.iov_len, + m->middle->vec.iov_base); /* fill in crc (except data pages), footer */ con->out_msg->hdr.crc = @@ -580,7 +593,7 @@ static void prepare_write_message(struct ceph_connection *con) con->out_more = 1; /* data + footer will follow */ } else { /* no, queue up footer too and be done */ - prepare_write_message_footer(con, v); + prepare_write_message_footer(con); } set_bit(WRITE_PENDING, &con->state); @@ -595,14 +608,14 @@ static void prepare_write_ack(struct ceph_connection *con) con->in_seq_acked, con->in_seq); con->in_seq_acked = con->in_seq; - con->out_kvec[0].iov_base = &tag_ack; - con->out_kvec[0].iov_len = 1; + ceph_con_out_kvec_reset(con); + + ceph_con_out_kvec_add(con, sizeof (tag_ack), &tag_ack); + con->out_temp_ack = cpu_to_le64(con->in_seq_acked); - con->out_kvec[1].iov_base = &con->out_temp_ack; - con->out_kvec[1].iov_len = sizeof(con->out_temp_ack); - con->out_kvec_left = 2; - con->out_kvec_bytes = 1 + sizeof(con->out_temp_ack); - con->out_kvec_cur = con->out_kvec; + ceph_con_out_kvec_add(con, sizeof (con->out_temp_ack), + &con->out_temp_ack); + con->out_more = 1; /* more will follow.. eventually.. */ set_bit(WRITE_PENDING, &con->state); } @@ -613,11 +626,8 @@ static void prepare_write_ack(struct ceph_connection *con) static void prepare_write_keepalive(struct ceph_connection *con) { dout("prepare_write_keepalive %p\n", con); - con->out_kvec[0].iov_base = &tag_keepalive; - con->out_kvec[0].iov_len = 1; - con->out_kvec_left = 1; - con->out_kvec_bytes = 1; - con->out_kvec_cur = con->out_kvec; + ceph_con_out_kvec_reset(con); + ceph_con_out_kvec_add(con, sizeof (tag_keepalive), &tag_keepalive); set_bit(WRITE_PENDING, &con->state); } @@ -646,12 +656,9 @@ static int prepare_connect_authorizer(struct ceph_connection *con) con->out_connect.authorizer_protocol = cpu_to_le32(auth_protocol); con->out_connect.authorizer_len = cpu_to_le32(auth_len); - if (auth_len) { - con->out_kvec[con->out_kvec_left].iov_base = auth_buf; - con->out_kvec[con->out_kvec_left].iov_len = auth_len; - con->out_kvec_left++; - con->out_kvec_bytes += auth_len; - } + if (auth_len) + ceph_con_out_kvec_add(con, auth_len, auth_buf); + return 0; } @@ -661,15 +668,11 @@ static int prepare_connect_authorizer(struct ceph_connection *con) static void prepare_write_banner(struct ceph_messenger *msgr, struct ceph_connection *con) { - int len = strlen(CEPH_BANNER); + ceph_con_out_kvec_reset(con); + ceph_con_out_kvec_add(con, strlen(CEPH_BANNER), CEPH_BANNER); + ceph_con_out_kvec_add(con, sizeof (msgr->my_enc_addr), + &msgr->my_enc_addr); - con->out_kvec[0].iov_base = CEPH_BANNER; - con->out_kvec[0].iov_len = len; - con->out_kvec[1].iov_base = &msgr->my_enc_addr; - con->out_kvec[1].iov_len = sizeof(msgr->my_enc_addr); - con->out_kvec_left = 2; - con->out_kvec_bytes = len + sizeof(msgr->my_enc_addr); - con->out_kvec_cur = con->out_kvec; con->out_more = 0; set_bit(WRITE_PENDING, &con->state); } @@ -707,22 +710,16 @@ static int prepare_write_connect(struct ceph_messenger *msgr, if (include_banner) prepare_write_banner(msgr, con); - else { - con->out_kvec_left = 0; - con->out_kvec_bytes = 0; - } - con->out_kvec[con->out_kvec_left].iov_base = &con->out_connect; - con->out_kvec[con->out_kvec_left].iov_len = sizeof(con->out_connect); - con->out_kvec_left++; - con->out_kvec_bytes += sizeof(con->out_connect); - con->out_kvec_cur = con->out_kvec; + else + ceph_con_out_kvec_reset(con); + ceph_con_out_kvec_add(con, sizeof (con->out_connect), &con->out_connect); + con->out_more = 0; set_bit(WRITE_PENDING, &con->state); return prepare_connect_authorizer(con); } - /* * write as much of pending kvecs to the socket as we can. * 1 -> done @@ -919,10 +916,8 @@ static int write_partial_msg_pages(struct ceph_connection *con) /* prepare and queue up footer, too */ if (!crc) con->out_msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC; - con->out_kvec_bytes = 0; - con->out_kvec_left = 0; - con->out_kvec_cur = con->out_kvec; - prepare_write_message_footer(con, 0); + ceph_con_out_kvec_reset(con); + prepare_write_message_footer(con); ret = 1; out: return ret; -- cgit v1.2.3 From e0f43c9419c1900e5b50de4261e9686a45a0a2b8 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 14 Feb 2012 14:05:33 -0600 Subject: libceph: make ceph_msgr_wq private The messenger workqueue has no need to be public. So give it static scope. Signed-off-by: Alex Elder Signed-off-by: Sage Weil --- net/ceph/messenger.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 04d2b975ab0c..31f59ac03d8a 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -97,7 +97,7 @@ static void encode_my_addr(struct ceph_messenger *msgr) /* * work queue for all reading and writing to/from the socket. */ -struct workqueue_struct *ceph_msgr_wq; +static struct workqueue_struct *ceph_msgr_wq; int ceph_msgr_init(void) { -- cgit v1.2.3 From 6173d1f02fb19c0fba02857ae4e1109b5ec95034 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 14 Feb 2012 14:05:33 -0600 Subject: libceph: encapsulate some messenger cleanup code Define a helper function to perform various cleanup operations. Use it both in the exit routine and in the init routine in the event of an error. Signed-off-by: Alex Elder Signed-off-by: Sage Weil --- net/ceph/messenger.c | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) (limited to 'net') diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 31f59ac03d8a..c3023a600ad2 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -99,6 +99,20 @@ static void encode_my_addr(struct ceph_messenger *msgr) */ static struct workqueue_struct *ceph_msgr_wq; +void _ceph_msgr_exit(void) +{ + if (ceph_msgr_wq) + destroy_workqueue(ceph_msgr_wq); + + BUG_ON(zero_page_address == NULL); + zero_page_address = NULL; + + BUG_ON(zero_page == NULL); + kunmap(zero_page); + page_cache_release(zero_page); + zero_page = NULL; +} + int ceph_msgr_init(void) { BUG_ON(zero_page != NULL); @@ -109,33 +123,21 @@ int ceph_msgr_init(void) zero_page_address = kmap(zero_page); ceph_msgr_wq = alloc_workqueue("ceph-msgr", WQ_NON_REENTRANT, 0); - if (!ceph_msgr_wq) { - pr_err("msgr_init failed to create workqueue\n"); - - zero_page_address = NULL; - kunmap(zero_page); - page_cache_release(zero_page); - zero_page = NULL; + if (ceph_msgr_wq) + return 0; - return -ENOMEM; - } + pr_err("msgr_init failed to create workqueue\n"); + _ceph_msgr_exit(); - return 0; + return -ENOMEM; } EXPORT_SYMBOL(ceph_msgr_init); void ceph_msgr_exit(void) { BUG_ON(ceph_msgr_wq == NULL); - destroy_workqueue(ceph_msgr_wq); - BUG_ON(zero_page_address == NULL); - zero_page_address = NULL; - - BUG_ON(zero_page == NULL); - kunmap(zero_page); - page_cache_release(zero_page); - zero_page = NULL; + _ceph_msgr_exit(); } EXPORT_SYMBOL(ceph_msgr_exit); -- cgit v1.2.3 From 41617d0c9c9832e030667277ddf6b4ffb4ecdc90 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 14 Feb 2012 14:05:33 -0600 Subject: libceph: make ceph_tcp_connect() return int There is no real need for ceph_tcp_connect() to return the socket pointer it creates, since it already assigns it to con->sock, which is visible to the caller. Instead, have it return an error code, which tidies things up a bit. Signed-off-by: Alex Elder Signed-off-by: Sage Weil --- net/ceph/messenger.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index c3023a600ad2..e1e53bb2d0cf 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -240,7 +240,7 @@ static void set_sock_callbacks(struct socket *sock, /* * initiate connection to a remote socket. */ -static struct socket *ceph_tcp_connect(struct ceph_connection *con) +static int ceph_tcp_connect(struct ceph_connection *con) { struct sockaddr_storage *paddr = &con->peer_addr.in_addr; struct socket *sock; @@ -250,7 +250,7 @@ static struct socket *ceph_tcp_connect(struct ceph_connection *con) ret = sock_create_kern(con->peer_addr.in_addr.ss_family, SOCK_STREAM, IPPROTO_TCP, &sock); if (ret) - return ERR_PTR(ret); + return ret; sock->sk->sk_allocation = GFP_NOFS; #ifdef CONFIG_LOCKDEP @@ -273,11 +273,11 @@ static struct socket *ceph_tcp_connect(struct ceph_connection *con) sock_release(sock); con->error_msg = "connect error"; - return ERR_PTR(ret); + return ret; } con->sock = sock; - return sock; + return 0; } static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len) @@ -1854,11 +1854,9 @@ more: con->in_tag = CEPH_MSGR_TAG_READY; dout("try_write initiating connect on %p new state %lu\n", con, con->state); - con->sock = ceph_tcp_connect(con); - if (IS_ERR(con->sock)) { - con->sock = NULL; + ret = ceph_tcp_connect(con); + if (ret < 0) { con->error_msg = "connect error"; - ret = -1; goto out; } } -- cgit v1.2.3 From d3002b974cefbb7c1e325cc296966f768ff76b06 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 14 Feb 2012 14:05:33 -0600 Subject: libceph: a few small changes This gathers a number of very minor changes: - use %hu when formatting the a socket address's address family - null out the ceph_msgr_wq pointer after the queue has been destroyed - drop a needless cast in ceph_write_space() - add a WARN() call in ceph_state_change() in the event an unrecognized socket state is encountered - rearrange the logic in ceph_con_get() and ceph_con_put() so that: - the reference counts are only atomically read once - the values displayed via dout() calls are known to be meaningful at the time they are formatted Signed-off-by: Alex Elder Signed-off-by: Sage Weil --- net/ceph/messenger.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) (limited to 'net') diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index e1e53bb2d0cf..44d8c77cabdd 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -80,8 +80,8 @@ const char *ceph_pr_addr(const struct sockaddr_storage *ss) break; default: - snprintf(s, MAX_ADDR_STR_LEN, "(unknown sockaddr family %d)", - (int)ss->ss_family); + snprintf(s, MAX_ADDR_STR_LEN, "(unknown sockaddr family %hu)", + ss->ss_family); } return s; @@ -101,8 +101,10 @@ static struct workqueue_struct *ceph_msgr_wq; void _ceph_msgr_exit(void) { - if (ceph_msgr_wq) + if (ceph_msgr_wq) { destroy_workqueue(ceph_msgr_wq); + ceph_msgr_wq = NULL; + } BUG_ON(zero_page_address == NULL); zero_page_address = NULL; @@ -167,8 +169,7 @@ static void ceph_data_ready(struct sock *sk, int count_unused) /* socket has buffer space for writing */ static void ceph_write_space(struct sock *sk) { - struct ceph_connection *con = - (struct ceph_connection *)sk->sk_user_data; + struct ceph_connection *con = sk->sk_user_data; /* only queue to workqueue if there is data we want to write, * and there is sufficient space in the socket buffer to accept @@ -216,6 +217,8 @@ static void ceph_state_change(struct sock *sk) dout("ceph_state_change TCP_ESTABLISHED\n"); queue_con(con); break; + default: /* Everything else is uninteresting */ + break; } } @@ -420,22 +423,23 @@ bool ceph_con_opened(struct ceph_connection *con) */ struct ceph_connection *ceph_con_get(struct ceph_connection *con) { - dout("con_get %p nref = %d -> %d\n", con, - atomic_read(&con->nref), atomic_read(&con->nref) + 1); - if (atomic_inc_not_zero(&con->nref)) - return con; - return NULL; + int nref = __atomic_add_unless(&con->nref, 1, 0); + + dout("con_get %p nref = %d -> %d\n", con, nref, nref + 1); + + return nref ? con : NULL; } void ceph_con_put(struct ceph_connection *con) { - dout("con_put %p nref = %d -> %d\n", con, - atomic_read(&con->nref), atomic_read(&con->nref) - 1); - BUG_ON(atomic_read(&con->nref) == 0); - if (atomic_dec_and_test(&con->nref)) { + int nref = atomic_dec_return(&con->nref); + + BUG_ON(nref < 0); + if (nref == 0) { BUG_ON(con->sock); kfree(con); } + dout("con_put %p nref = %d -> %d\n", con, nref + 1, nref); } /* -- cgit v1.2.3 From cffaba15cd95d4a16eb5a6aa5c22a79f67d555ab Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 15 Feb 2012 07:43:54 -0600 Subject: ceph: ensure Boolean options support both senses Many ceph-related Boolean options offer the ability to both enable and disable a feature. For all those that don't offer this, add a new option so that they do. Note that ceph_show_options()--which reports mount options currently in effect--only reports the option if it is different from the default value. Signed-off-by: Alex Elder Signed-off-by: Sage Weil --- net/ceph/ceph_common.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'net') diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 621c3221b393..cc913193d992 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -201,7 +201,9 @@ enum { Opt_ip, Opt_last_string, /* string args above */ + Opt_share, Opt_noshare, + Opt_crc, Opt_nocrc, }; @@ -217,7 +219,9 @@ static match_table_t opt_tokens = { {Opt_key, "key=%s"}, {Opt_ip, "ip=%s"}, /* string args above */ + {Opt_share, "share"}, {Opt_noshare, "noshare"}, + {Opt_crc, "crc"}, {Opt_nocrc, "nocrc"}, {-1, NULL} }; @@ -399,10 +403,16 @@ ceph_parse_options(char *options, const char *dev_name, opt->mount_timeout = intval; break; + case Opt_share: + opt->flags &= ~CEPH_OPT_NOSHARE; + break; case Opt_noshare: opt->flags |= CEPH_OPT_NOSHARE; break; + case Opt_crc: + opt->flags &= ~CEPH_OPT_NOCRC; + break; case Opt_nocrc: opt->flags |= CEPH_OPT_NOCRC; break; -- cgit v1.2.3 From bca064d236a2e3162a07c758855221bcbe3c475b Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 15 Feb 2012 07:43:54 -0600 Subject: libceph: use "do" in CRC-related Boolean var