• Venkat Venkatsubra's avatar
    rds: prevent BUG_ON triggered on congestion update to loopback · 18fc25c9
    Venkat Venkatsubra authored
    After congestion update on a local connection, when rds_ib_xmit returns
    less bytes than that are there in the message, rds_send_xmit calls
    back rds_ib_xmit with an offset that causes BUG_ON(off & RDS_FRAG_SIZE)
    to trigger.
    
    For a 4Kb PAGE_SIZE rds_ib_xmit returns min(8240,4096)=4096 when actually
    the message contains 8240 bytes. rds_send_xmit thinks there is more to send
    and calls rds_ib_xmit again with a data offset "off" of 4096-48(rds header)
    =4048 bytes thus hitting the BUG_ON(off & RDS_FRAG_SIZE) [RDS_FRAG_SIZE=4k].
    
    The commit 6094628b
    "rds: prevent BUG_ON triggering on congestion map updates" introduced
    this regression. That change was addressing the triggering of a different
    BUG_ON in rds_send_xmit() on PowerPC architecture with 64Kbytes PAGE_SIZE:
     	BUG_ON(ret != 0 &&
        		 conn->c_xmit_sg == rm->data.op_nents);
    This was the sequence it was going through:
    (rds_ib_xmit)
    /* Do not send cong updates to IB loopback */
    if (conn->c_loopback
       && rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) {
      	rds_cong_map_updated(conn->c_fcong, ~(u64) 0);
        	return sizeof(struct rds_header) + RDS_CONG_MAP_BYTES;
    }
    rds_ib_xmit returns 8240
    rds_send_xmit:
      c_xmit_data_off = 0 + 8240 - 48 (rds header accounted only the first time)
       		 = 8192
      c_xmit_data_off < 65536 (sg->length), so calls rds_ib_xmit again
    rds_ib_xmit returns 8240
    rds_send_xmit:
      c_xmit_data_off = 8192 + 8240 = 16432, calls rds_ib_xmit again
      and so on (c_xmit_data_off 24672,32912,41152,49392,57632)
    rds_ib_xmit returns 8240
    On this iteration this sequence causes the BUG_ON in rds_send_xmit:
        while (ret) {
        	tmp = min_t(int, ret, sg->length - conn->c_xmit_data_off);
        	[tmp = 65536 - 57632 = 7904]
        	conn->c_xmit_data_off += tmp;
        	[c_xmit_data_off = 57632 + 7904 = 65536]
        	ret -= tmp;
        	[ret = 8240 - 7904 = 336]
        	if (conn->c_xmit_data_off == sg->length) {
        		conn->c_xmit_data_off = 0;
        		sg++;
        		conn->c_xmit_sg++;
        		BUG_ON(ret != 0 &&
        			conn->c_xmit_sg == rm->data.op_nents);
        		[c_xmit_sg = 1, rm->data.op_nents = 1]
    
    What the current fix does:
    Since the congestion update over loopback is not actually transmitted
    as a message, all that rds_ib_xmit needs to do is let the caller think
    the full message has been transmitted and not return partial bytes.
    It will return 8240 (RDS_CONG_MAP_BYTES+48) when PAGE_SIZE is 4Kb.
    And 64Kb+48 when page size is 64Kb.
    Reported-by: default avatarJosh Hunt <joshhunt00@gmail.com>
    Tested-by: default avatarHonggang Li <honli@redhat.com>
    Acked-by: default avatarBang Nguyen <bang.nguyen@oracle.com>
    Signed-off-by: default avatarVenkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
    Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
    18fc25c9
ib_send.c 30.2 KB