From ea010070d0a7497253d5a6f919f6dd107450b31a Mon Sep 17 00:00:00 2001 From: shamir rabinovitch Date: Sun, 16 Dec 2018 09:01:08 +0200 Subject: net/rds: fix warn in rds_message_alloc_sgs redundant copy_from_user in rds_sendmsg system call expose rds to issue where rds_rdma_extra_size walk the rds iovec and and calculate the number pf pages (sgs) it need to add to the tail of rds message and later rds_cmsg_rdma_args copy the rds iovec again and re calculate the same number and get different result causing WARN_ON in rds_message_alloc_sgs. fix this by doing the copy_from_user only once per rds_sendmsg system call. When issue occur the below dump is seen: WARNING: CPU: 0 PID: 19789 at net/rds/message.c:316 rds_message_alloc_sgs+0x10c/0x160 net/rds/message.c:316 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 19789 Comm: syz-executor827 Not tainted 4.19.0-next-20181030+ #101 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x244/0x39d lib/dump_stack.c:113 panic+0x2ad/0x55c kernel/panic.c:188 __warn.cold.8+0x20/0x45 kernel/panic.c:540 report_bug+0x254/0x2d0 lib/bug.c:186 fixup_bug arch/x86/kernel/traps.c:178 [inline] do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:271 do_invalid_op+0x36/0x40 arch/x86/kernel/traps.c:290 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:969 RIP: 0010:rds_message_alloc_sgs+0x10c/0x160 net/rds/message.c:316 Code: c0 74 04 3c 03 7e 6c 44 01 ab 78 01 00 00 e8 2b 9e 35 fa 4c 89 e0 48 83 c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d c3 e8 14 9e 35 fa <0f> 0b 31 ff 44 89 ee e8 18 9f 35 fa 45 85 ed 75 1b e8 fe 9d 35 fa RSP: 0018:ffff8801c51b7460 EFLAGS: 00010293 RAX: ffff8801bc412080 RBX: ffff8801d7bf4040 RCX: ffffffff8749c9e6 RDX: 0000000000000000 RSI: ffffffff8749ca5c RDI: 0000000000000004 RBP: ffff8801c51b7490 R08: ffff8801bc412080 R09: ffffed003b5c5b67 R10: ffffed003b5c5b67 R11: ffff8801dae2db3b R12: 0000000000000000 R13: 000000000007165c R14: 000000000007165c R15: 0000000000000005 rds_cmsg_rdma_args+0x82d/0x1510 net/rds/rdma.c:623 rds_cmsg_send net/rds/send.c:971 [inline] rds_sendmsg+0x19a2/0x3180 net/rds/send.c:1273 sock_sendmsg_nosec net/socket.c:622 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:632 ___sys_sendmsg+0x7fd/0x930 net/socket.c:2117 __sys_sendmsg+0x11d/0x280 net/socket.c:2155 __do_sys_sendmsg net/socket.c:2164 [inline] __se_sys_sendmsg net/socket.c:2162 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2162 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x44a859 Code: e8 dc e6 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 6b cb fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f1d4710ada8 EFLAGS: 00000297 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000006dcc28 RCX: 000000000044a859 RDX: 0000000000000000 RSI: 0000000020001600 RDI: 0000000000000003 RBP: 00000000006dcc20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000297 R12: 00000000006dcc2c R13: 646e732f7665642f R14: 00007f1d4710b9c0 R15: 00000000006dcd2c Kernel Offset: disabled Rebooting in 86400 seconds.. Reported-by: syzbot+26de17458aeda9d305d8@syzkaller.appspotmail.com Acked-by: Santosh Shilimkar Signed-off-by: shamir rabinovitch Signed-off-by: David S. Miller --- net/rds/send.c | 50 +++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 43 insertions(+), 7 deletions(-) (limited to 'net/rds/send.c') diff --git a/net/rds/send.c b/net/rds/send.c index fe785ee819dd..ec2267cbf85f 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -876,13 +876,15 @@ out: * rds_message is getting to be quite complicated, and we'd like to allocate * it all in one go. This figures out how big it needs to be up front. */ -static int rds_rm_size(struct msghdr *msg, int num_sgs) +static int rds_rm_size(struct msghdr *msg, int num_sgs, + struct rds_iov_vector_arr *vct) { struct cmsghdr *cmsg; int size = 0; int cmsg_groups = 0; int retval; bool zcopy_cookie = false; + struct rds_iov_vector *iov, *tmp_iov; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) @@ -893,8 +895,24 @@ static int rds_rm_size(struct msghdr *msg, int num_sgs) switch (cmsg->cmsg_type) { case RDS_CMSG_RDMA_ARGS: + if (vct->indx >= vct->len) { + vct->len += vct->incr; + tmp_iov = + krealloc(vct->vec, + vct->len * + sizeof(struct rds_iov_vector), + GFP_KERNEL); + if (!tmp_iov) { + vct->len -= vct->incr; + return -ENOMEM; + } + vct->vec = tmp_iov; + } + iov = &vct->vec[vct->indx]; + memset(iov, 0, sizeof(struct rds_iov_vector)); + vct->indx++; cmsg_groups |= 1; - retval = rds_rdma_extra_size(CMSG_DATA(cmsg)); + retval = rds_rdma_extra_size(CMSG_DATA(cmsg), iov); if (retval < 0) return retval; size += retval; @@ -951,10 +969,11 @@ static int rds_cmsg_zcopy(struct rds_sock *rs, struct rds_message *rm, } static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, - struct msghdr *msg, int *allocated_mr) + struct msghdr *msg, int *allocated_mr, + struct rds_iov_vector_arr *vct) { struct cmsghdr *cmsg; - int ret = 0; + int ret = 0, ind = 0; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) @@ -968,7 +987,10 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, */ switch (cmsg->cmsg_type) { case RDS_CMSG_RDMA_ARGS: - ret = rds_cmsg_rdma_args(rs, rm, cmsg); + if (ind >= vct->indx) + return -ENOMEM; + ret = rds_cmsg_rdma_args(rs, rm, cmsg, &vct->vec[ind]); + ind++; break; case RDS_CMSG_RDMA_DEST: @@ -1084,6 +1106,11 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY)); int num_sgs = ceil(payload_len, PAGE_SIZE); int namelen; + struct rds_iov_vector_arr vct = {0}; + int ind; + + /* expect 1 RDMA CMSG per rds_sendmsg. can still grow if more needed. */ + vct.incr = 1; /* Mirror Linux UDP mirror of BSD error message compatibility */ /* XXX: Perhaps MSG_MORE someday */ @@ -1220,7 +1247,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) num_sgs = iov_iter_npages(&msg->msg_iter, INT_MAX); } /* size of rm including all sgs */ - ret = rds_rm_size(msg, num_sgs); + ret = rds_rm_size(msg, num_sgs, &vct); if (ret < 0) goto out; @@ -1270,7 +1297,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) rm->m_conn_path = cpath; /* Parse any control messages the user may have included. */ - ret = rds_cmsg_send(rs, rm, msg, &allocated_mr); + ret = rds_cmsg_send(rs, rm, msg, &allocated_mr, &vct); if (ret) { /* Trigger connection so that its ready for the next retry */ if (ret == -EAGAIN) @@ -1348,9 +1375,18 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) if (ret) goto out; rds_message_put(rm); + + for (ind = 0; ind < vct.indx; ind++) + kfree(vct.vec[ind].iov); + kfree(vct.vec); + return payload_len; out: + for (ind = 0; ind < vct.indx; ind++) + kfree(vct.vec[ind].iov); + kfree(vct.vec); + /* If the user included a RDMA_MAP cmsg, we allocated a MR on the fly. * If the sendmsg goes through, we keep the MR. If it fails with EAGAIN * or in any other way, we need to destroy the MR again */ -- cgit v1.2.3