linux.git/net/rds, branch v2.6.38 Linux kernel source tree rds: prevent BUG_ON triggering on congestion map updates 2011-03-08T19:22:43+00:00 Neil Horman nhorman@tuxdriver.com 2011-03-02T06:28:22+00:00 6094628bfd94323fc1cea05ec2c6affd98c18f7f Recently had this bug halt reported to me: kernel BUG at net/rds/send.c:329! Oops: Exception in kernel mode, sig: 5 [#1] SMP NR_CPUS=1024 NUMA pSeries Modules linked in: rds sunrpc ipv6 dm_mirror dm_region_hash dm_log ibmveth sg ext4 jbd2 mbcache sd_mod crc_t10dif ibmvscsic scsi_transport_srp scsi_tgt dm_mod [last unloaded: scsi_wait_scan] NIP: d000000003ca68f4 LR: d000000003ca67fc CTR: d000000003ca8770 REGS: c000000175cab980 TRAP: 0700 Not tainted (2.6.32-118.el6.ppc64) MSR: 8000000000029032 <EE,ME,CE,IR,DR> CR: 44000022 XER: 00000000 TASK = c00000017586ec90[1896] 'krdsd' THREAD: c000000175ca8000 CPU: 0 GPR00: 0000000000000150 c000000175cabc00 d000000003cb7340 0000000000002030 GPR04: ffffffffffffffff 0000000000000030 0000000000000000 0000000000000030 GPR08: 0000000000000001 0000000000000001 c0000001756b1e30 0000000000010000 GPR12: d000000003caac90 c000000000fa2500 c0000001742b2858 c0000001742b2a00 GPR16: c0000001742b2a08 c0000001742b2820 0000000000000001 0000000000000001 GPR20: 0000000000000040 c0000001742b2814 c000000175cabc70 0800000000000000 GPR24: 0000000000000004 0200000000000000 0000000000000000 c0000001742b2860 GPR28: 0000000000000000 c0000001756b1c80 d000000003cb68e8 c0000001742b27b8 NIP [d000000003ca68f4] .rds_send_xmit+0x4c4/0x8a0 [rds] LR [d000000003ca67fc] .rds_send_xmit+0x3cc/0x8a0 [rds] Call Trace: [c000000175cabc00] [d000000003ca67fc] .rds_send_xmit+0x3cc/0x8a0 [rds] (unreliable) [c000000175cabd30] [d000000003ca7e64] .rds_send_worker+0x54/0x100 [rds] [c000000175cabdb0] [c0000000000b475c] .worker_thread+0x1dc/0x3c0 [c000000175cabed0] [c0000000000baa9c] .kthread+0xbc/0xd0 [c000000175cabf90] [c000000000032114] .kernel_thread+0x54/0x70 Instruction dump: 4bfffd50 60000000 60000000 39080001 935f004c f91f0040 41820024 813d017c 7d094a78 7d290074 7929d182 394a0020 <0b090000> 40e2ff68 4bffffa4 39200000 Kernel panic - not syncing: Fatal exception Call Trace: [c000000175cab560] [c000000000012e04] .show_stack+0x74/0x1c0 (unreliable) [c000000175cab610] [c0000000005a365c] .panic+0x80/0x1b4 [c000000175cab6a0] [c00000000002fbcc] .die+0x21c/0x2a0 [c000000175cab750] [c000000000030000] ._exception+0x110/0x220 [c000000175cab910] [c000000000004b9c] program_check_common+0x11c/0x180 Signed-off-by: David S. Miller <davem@davemloft.net> 
Recently had this bug halt reported to me:

kernel BUG at net/rds/send.c:329!
Oops: Exception in kernel mode, sig: 5 [#1]
SMP NR_CPUS=1024 NUMA pSeries
Modules linked in: rds sunrpc ipv6 dm_mirror dm_region_hash dm_log ibmveth sg
ext4 jbd2 mbcache sd_mod crc_t10dif ibmvscsic scsi_transport_srp scsi_tgt
dm_mod [last unloaded: scsi_wait_scan]
NIP: d000000003ca68f4 LR: d000000003ca67fc CTR: d000000003ca8770
REGS: c000000175cab980 TRAP: 0700   Not tainted  (2.6.32-118.el6.ppc64)
MSR: 8000000000029032 <EE,ME,CE,IR,DR>  CR: 44000022  XER: 00000000
TASK = c00000017586ec90[1896] 'krdsd' THREAD: c000000175ca8000 CPU: 0
GPR00: 0000000000000150 c000000175cabc00 d000000003cb7340 0000000000002030
GPR04: ffffffffffffffff 0000000000000030 0000000000000000 0000000000000030
GPR08: 0000000000000001 0000000000000001 c0000001756b1e30 0000000000010000
GPR12: d000000003caac90 c000000000fa2500 c0000001742b2858 c0000001742b2a00
GPR16: c0000001742b2a08 c0000001742b2820 0000000000000001 0000000000000001
GPR20: 0000000000000040 c0000001742b2814 c000000175cabc70 0800000000000000
GPR24: 0000000000000004 0200000000000000 0000000000000000 c0000001742b2860
GPR28: 0000000000000000 c0000001756b1c80 d000000003cb68e8 c0000001742b27b8
NIP [d000000003ca68f4] .rds_send_xmit+0x4c4/0x8a0 [rds]
LR [d000000003ca67fc] .rds_send_xmit+0x3cc/0x8a0 [rds]
Call Trace:
[c000000175cabc00] [d000000003ca67fc] .rds_send_xmit+0x3cc/0x8a0 [rds]
(unreliable)
[c000000175cabd30] [d000000003ca7e64] .rds_send_worker+0x54/0x100 [rds]
[c000000175cabdb0] [c0000000000b475c] .worker_thread+0x1dc/0x3c0
[c000000175cabed0] [c0000000000baa9c] .kthread+0xbc/0xd0
[c000000175cabf90] [c000000000032114] .kernel_thread+0x54/0x70
Instruction dump:
4bfffd50 60000000 60000000 39080001 935f004c f91f0040 41820024 813d017c
7d094a78 7d290074 7929d182 394a0020 <0b090000> 40e2ff68 4bffffa4 39200000
Kernel panic - not syncing: Fatal exception
Call Trace:
[c000000175cab560] [c000000000012e04] .show_stack+0x74/0x1c0 (unreliable)
[c000000175cab610] [c0000000005a365c] .panic+0x80/0x1b4
[c000000175cab6a0] [c00000000002fbcc] .die+0x21c/0x2a0
[c000000175cab750] [c000000000030000] ._exception+0x110/0x220
[c000000175cab910] [c000000000004b9c] program_check_common+0x11c/0x180

Signed-off-by: David S. Miller <davem@davemloft.net>
Net: rds: Makefile: Remove deprecated items 2010-11-22T16:16:15+00:00 Tracey Dent tdent48227@gmail.com 2010-11-21T15:03:25+00:00 094f2faaa2c4973e50979158f655a1d31a97ba98 Changed Makefile to use <modules>-y instead of <modules>-objs because -objs is deprecated and not mentioned in Documentation/kbuild/makefiles.txt. Also, use the ccflags-$ flag instead of EXTRA_CFLAGS because EXTRA_CFLAGS is deprecated and should now be switched. Last but not least, took out if-conditionals. Signed-off-by: Tracey Dent <tdent48227@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Changed Makefile to use <modules>-y instead of <modules>-objs
because -objs is deprecated and not mentioned in
Documentation/kbuild/makefiles.txt.

Also, use the ccflags-$ flag instead of EXTRA_CFLAGS because EXTRA_CFLAGS is
deprecated and should now be switched.

Last but not least, took out if-conditionals.

Signed-off-by: Tracey Dent <tdent48227@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
rds: Integer overflow in RDS cmsg handling 2010-11-17T20:20:52+00:00 Dan Rosenberg drosenberg@vsecurity.com 2010-11-17T06:37:16+00:00 218854af84038d828a32f061858b1902ed2beec6 In rds_cmsg_rdma_args(), the user-provided args->nr_local value is restricted to less than UINT_MAX. This seems to need a tighter upper bound, since the calculation of total iov_size can overflow, resulting in a small sock_kmalloc() allocation. This would probably just result in walking off the heap and crashing when calling rds_rdma_pages() with a high count value. If it somehow doesn't crash here, then memory corruption could occur soon after. Signed-off-by: Dan Rosenberg <drosenberg@vsecurity.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
In rds_cmsg_rdma_args(), the user-provided args->nr_local value is
restricted to less than UINT_MAX.  This seems to need a tighter upper
bound, since the calculation of total iov_size can overflow, resulting
in a small sock_kmalloc() allocation.  This would probably just result
in walking off the heap and crashing when calling rds_rdma_pages() with
a high count value.  If it somehow doesn't crash here, then memory
corruption could occur soon after.

Signed-off-by: Dan Rosenberg <drosenberg@vsecurity.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
rds: Fix rds message leak in rds_message_map_pages 2010-11-08T20:17:09+00:00 Pavel Emelyanov xemul@parallels.com 2010-11-08T06:20:50+00:00 aa58163a76a3aef33c7220931543d45d0fe43753 The sgs allocation error path leaks the allocated message. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: Andy Grover <andy.grover@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
The sgs allocation error path leaks the allocated message.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Acked-by: Andy Grover <andy.grover@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
rds: Remove kfreed tcp conn from list 2010-11-04T01:50:07+00:00 Pavel Emelyanov xemul@parallels.com 2010-11-02T01:54:01+00:00 8200a59f24aeca379660f80658a8c0c343ca5c31 All the rds_tcp_connection objects are stored list, but when being freed it should be removed from there. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net> 
All the rds_tcp_connection objects are stored list, but when
being freed it should be removed from there.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
rds: Lost locking in loop connection freeing 2010-11-04T01:50:06+00:00 Pavel Emelyanov xemul@parallels.com 2010-11-02T01:52:05+00:00 58c490babd4b425310363cbd1f406d7e508f77a5 The conn is removed from list in there and this requires proper lock protection. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net> 
The conn is removed from list in there and this requires
proper lock protection.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
RDS: Let rds_message_alloc_sgs() return NULL 2010-10-30T23:34:18+00:00 Andy Grover andy.grover@oracle.com 2010-10-28T15:40:59+00:00 d139ff0907dac9ef72fb2cf301e345bac3aec42f Even with the previous fix, we still are reading the iovecs once to determine SGs needed, and then again later on. Preallocating space for sg lists as part of rds_message seemed like a good idea but it might be better to not do this. While working to redo that code, this patch attempts to protect against userspace rewriting the rds_iovec array between the first and second accesses. The consequences of this would be either a too-small or too-large sg list array. Too large is not an issue. This patch changes all callers of message_alloc_sgs to handle running out of preallocated sgs, and fail gracefully. Signed-off-by: Andy Grover <andy.grover@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Even with the previous fix, we still are reading the iovecs once
to determine SGs needed, and then again later on. Preallocating
space for sg lists as part of rds_message seemed like a good idea
but it might be better to not do this. While working to redo that
code, this patch attempts to protect against userspace rewriting
the rds_iovec array between the first and second accesses.

The consequences of this would be either a too-small or too-large
sg list array. Too large is not an issue. This patch changes all
callers of message_alloc_sgs to handle running out of preallocated
sgs, and fail gracefully.

Signed-off-by: Andy Grover <andy.grover@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RDS: Copy rds_iovecs into kernel memory instead of rereading from userspace 2010-10-30T23:34:17+00:00 Andy Grover andy.grover@oracle.com 2010-10-28T15:40:58+00:00 fc8162e3c034af743d8def435fda6396603d321f Change rds_rdma_pages to take a passed-in rds_iovec array instead of doing copy_from_user itself. Change rds_cmsg_rdma_args to copy rds_iovec array once only. This eliminates the possibility of userspace changing it after our sanity checks. Implement stack-based storage for small numbers of iovecs, based on net/socket.c, to save an alloc in the extremely common case. Although this patch reduces iovec copies in cmsg_rdma_args to 1, we still do another one in rds_rdma_extra_size. Getting rid of that one will be trickier, so it'll be a separate patch. Signed-off-by: Andy Grover <andy.grover@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Change rds_rdma_pages to take a passed-in rds_iovec array instead
of doing copy_from_user itself.

Change rds_cmsg_rdma_args to copy rds_iovec array once only. This
eliminates the possibility of userspace changing it after our
sanity checks.

Implement stack-based storage for small numbers of iovecs, based
on net/socket.c, to save an alloc in the extremely common case.

Although this patch reduces iovec copies in cmsg_rdma_args to 1,
we still do another one in rds_rdma_extra_size. Getting rid of
that one will be trickier, so it'll be a separate patch.

Signed-off-by: Andy Grover <andy.grover@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RDS: Clean up error handling in rds_cmsg_rdma_args 2010-10-30T23:34:17+00:00 Andy Grover andy.grover@oracle.com 2010-10-28T15:40:57+00:00 f4a3fc03c1d73753879fb655b8cd628b29f6706b We don't need to set ret = 0 at the end -- it's initialized to 0. Also, don't increment s_send_rdma stat if we're exiting with an error. Signed-off-by: Andy Grover <andy.grover@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
We don't need to set ret = 0 at the end -- it's initialized to 0.

Also, don't increment s_send_rdma stat if we're exiting with an
error.

Signed-off-by: Andy Grover <andy.grover@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RDS: Return -EINVAL if rds_rdma_pages returns an error 2010-10-30T23:34:16+00:00 Andy Grover andy.grover@oracle.com 2010-10-28T15:40:56+00:00 a09f69c49b84b161ebd4dd09d3cce1b68297f1d3 rds_cmsg_rdma_args would still return success even if rds_rdma_pages returned an error (or overflowed). Signed-off-by: Andy Grover <andy.grover@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
rds_cmsg_rdma_args would still return success even if rds_rdma_pages
returned an error (or overflowed).

Signed-off-by: Andy Grover <andy.grover@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>