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 <santosh.shilimkar@oracle.com>
Signed-off-by: shamir rabinovitch <shamir.rabinovitch@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 91 insertions, 42 deletions

diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 98237feb607a..e1965d9cbcf8 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -517,9 +517,10 @@ static int rds_rdma_pages(struct rds_iovec iov[], int nr_iovecs)
         return tot_pages;
 }
 
-int rds_rdma_extra_size(struct rds_rdma_args *args)
+int rds_rdma_extra_size(struct rds_rdma_args *args,
+                        struct rds_iov_vector *iov)
 {
-        struct rds_iovec vec;
+        struct rds_iovec *vec;
         struct rds_iovec __user *local_vec;
         int tot_pages = 0;
         unsigned int nr_pages;
@@ -530,13 +531,23 @@ int rds_rdma_extra_size(struct rds_rdma_args *args)
         if (args->nr_local == 0)
                 return -EINVAL;
 
+        iov->iov = kcalloc(args->nr_local,
+                           sizeof(struct rds_iovec),
+                           GFP_KERNEL);
+        if (!iov->iov)
+                return -ENOMEM;
+
+        vec = &iov->iov[0];
+
+        if (copy_from_user(vec, local_vec, args->nr_local *
+                           sizeof(struct rds_iovec)))
+                return -EFAULT;
+        iov->len = args->nr_local;
+
         /* figure out the number of pages in the vector */
-        for (i = 0; i < args->nr_local; i++) {
-                if (copy_from_user(&vec, &local_vec[i],
-                                   sizeof(struct rds_iovec)))
-                        return -EFAULT;
+        for (i = 0; i < args->nr_local; i++, vec++) {
 
-                nr_pages = rds_pages_in_vec(&vec);
+                nr_pages = rds_pages_in_vec(vec);
                 if (nr_pages == 0)
                         return -EINVAL;
 
@@ -558,15 +569,15 @@ int rds_rdma_extra_size(struct rds_rdma_args *args)
  * Extract all arguments and set up the rdma_op
  */
 int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
-                          struct cmsghdr *cmsg)
+                       struct cmsghdr *cmsg,
+                       struct rds_iov_vector *vec)
 {
         struct rds_rdma_args *args;
         struct rm_rdma_op *op = &rm->rdma;
         int nr_pages;
         unsigned int nr_bytes;
         struct page **pages = NULL;
-        struct rds_iovec iovstack[UIO_FASTIOV], *iovs = iovstack;
-        int iov_size;
+        struct rds_iovec *iovs;
         unsigned int i, j;
         int ret = 0;
 
@@ -586,31 +597,23 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
                 goto out_ret;
         }
 
-        /* Check whether to allocate the iovec area */
-        iov_size = args->nr_local * sizeof(struct rds_iovec);
-        if (args->nr_local > UIO_FASTIOV) {
-                iovs = sock_kmalloc(rds_rs_to_sk(rs), iov_size, GFP_KERNEL);
-                if (!iovs) {
-                        ret = -ENOMEM;
-                        goto out_ret;
-                }
+        if (vec->len != args->nr_local) {
+                ret = -EINVAL;
+                goto out_ret;
         }
 
-        if (copy_from_user(iovs, (struct rds_iovec __user *)(unsigned long) args->local_vec_addr, iov_size)) {
-                ret = -EFAULT;
-                goto out;
-        }
+        iovs = vec->iov;
 
         nr_pages = rds_rdma_pages(iovs, args->nr_local);
         if (nr_pages < 0) {
                 ret = -EINVAL;
-                goto out;
+                goto out_ret;
         }
 
         pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
         if (!pages) {
                 ret = -ENOMEM;
-                goto out;
+                goto out_ret;
         }
 
         op->op_write = !!(args->flags & RDS_RDMA_READWRITE);
@@ -623,7 +626,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
         op->op_sg = rds_message_alloc_sgs(rm, nr_pages);
         if (!op->op_sg) {
                 ret = -ENOMEM;
-                goto out;
+                goto out_pages;
         }
 
         if (op->op_notify || op->op_recverr) {
@@ -635,7 +638,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
                 op->op_notifier = kmalloc(sizeof(struct rds_notifier), GFP_KERNEL);
                 if (!op->op_notifier) {
                         ret = -ENOMEM;
-                        goto out;
+                        goto out_pages;
                 }
                 op->op_notifier->n_user_token = args->user_token;
                 op->op_notifier->n_status = RDS_RDMA_SUCCESS;
@@ -681,7 +684,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
                  */
                 ret = rds_pin_pages(iov->addr, nr, pages, !op->op_write);
                 if (ret < 0)
-                        goto out;
+                        goto out_pages;
                 else
                         ret = 0;
 
@@ -714,13 +717,11 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
                                 nr_bytes,
                                 (unsigned int) args->remote_vec.bytes);
                 ret = -EINVAL;
-                goto out;
+                goto out_pages;
         }
         op->op_bytes = nr_bytes;
 
-out:
-        if (iovs != iovstack)
-                sock_kfree_s(rds_rs_to_sk(rs), iovs, iov_size);
+out_pages:
         kfree(pages);
 out_ret:
         if (ret)
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 6bfaf05b63b2..4d2523100093 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -386,6 +386,18 @@ static inline void rds_message_zcopy_queue_init(struct rds_msg_zcopy_queue *q)
         INIT_LIST_HEAD(&q->zcookie_head);
 }
 
+struct rds_iov_vector {
+        struct rds_iovec *iov;
+        int               len;
+};
+
+struct rds_iov_vector_arr {
+        struct rds_iov_vector *vec;
+        int                    len;
+        int                    indx;
+        int                    incr;
+};
+
 struct rds_message {
         refcount_t              m_refcount;
         struct list_head        m_sock_item;
@@ -904,13 +916,13 @@ int rds_get_mr(struct rds_sock *rs, char __user *optval, int optlen);
 int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen);
 int rds_free_mr(struct rds_sock *rs, char __user *optval, int optlen);
 void rds_rdma_drop_keys(struct rds_sock *rs);
-int rds_rdma_extra_size(struct rds_rdma_args *args);
-int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
-                          struct cmsghdr *cmsg);
+int rds_rdma_extra_size(struct rds_rdma_args *args,
+                        struct rds_iov_vector *iov);