| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20200803121858.190381162@linuxfoundation.org>
Date: Mon, 3 Aug 2020 14:18:35 +0200
From: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To: linux-kernel@...r.kernel.org
Cc: Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
stable@...r.kernel.org, Zhaojuan Guo <zguo@...hat.com>,
Kaike Wan <kaike.wan@...el.com>,
Mike Marciniszyn <mike.marciniszyn@...el.com>,
Honggang Li <honli@...hat.com>,
Jason Gunthorpe <jgg@...dia.com>
Subject: [PATCH 5.4 13/90] IB/rdmavt: Fix RQ counting issues causing use of an invalid RWQE
From: Mike Marciniszyn <mike.marciniszyn@...el.com>
commit 54a485e9ec084da1a4b32dcf7749c7d760ed8aa5 upstream.
The lookaside count is improperly initialized to the size of the
Receive Queue with the additional +1. In the traces below, the
RQ size is 384, so the count was set to 385.
The lookaside count is then rarely refreshed. Note the high and
incorrect count in the trace below:
rvt_get_rwqe: [hfi1_0] wqe ffffc900078e9008 wr_id 55c7206d75a0 qpn c
qpt 2 pid 3018 num_sge 1 head 1 tail 0, count 385
rvt_get_rwqe: (hfi1_rc_rcv+0x4eb/0x1480 [hfi1] <- rvt_get_rwqe) ret=0x1
The head,tail indicate there is only one RWQE posted although the count
says 385 and we correctly return the element 0.
The next call to rvt_get_rwqe with the decremented count:
rvt_get_rwqe: [hfi1_0] wqe ffffc900078e9058 wr_id 0 qpn c
qpt 2 pid 3018 num_sge 0 head 1 tail 1, count 384
rvt_get_rwqe: (hfi1_rc_rcv+0x4eb/0x1480 [hfi1] <- rvt_get_rwqe) ret=0x1
Note that the RQ is empty (head == tail) yet we return the RWQE at tail 1,
which is not valid because of the bogus high count.
Best case, the RWQE has never been posted and the rc logic sees an RWQE
that is too small (all zeros) and puts the QP into an error state.
In the worst case, a server slow at posting receive buffers might fool
rvt_get_rwqe() into fetching an old RWQE and corrupt memory.
Fix by deleting the faulty initialization code and creating an
inline to fetch the posted count and convert all callers to use
new inline.
Fixes: f592ae3c999f ("IB/rdmavt: Fracture single lock used for posting and processing RWQEs")
Link: https://lore.kernel.org/r/20200728183848.22226.29132.stgit@awfm-01.aw.intel.com
Reported-by: Zhaojuan Guo <zguo@...hat.com>
Cc: <stable@...r.kernel.org> # 5.4.x
Reviewed-by: Kaike Wan <kaike.wan@...el.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@...el.com>
Tested-by: Honggang Li <honli@...hat.com>
Signed-off-by: Jason Gunthorpe <jgg@...dia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
drivers/infiniband/sw/rdmavt/qp.c | 33 ++++-----------------------------
drivers/infiniband/sw/rdmavt/rc.c | 4 +---
include/rdma/rdmavt_qp.h | 19 +++++++++++++++++++
3 files changed, 24 insertions(+), 32 deletions(-)
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -898,8 +898,6 @@ static void rvt_init_qp(struct rvt_dev_i
qp->s_tail_ack_queue = 0;
qp->s_acked_ack_queue = 0;
qp->s_num_rd_atomic = 0;
- if (qp->r_rq.kwq)
- qp->r_rq.kwq->count = qp->r_rq.size;
qp->r_sge.num_sge = 0;
atomic_set(&qp->s_reserved_used, 0);
}
@@ -2353,31 +2351,6 @@ bad_lkey:
}
/**
- * get_count - count numbers of request work queue entries
- * in circular buffer
- * @rq: data structure for request queue entry
- * @tail: tail indices of the circular buffer
- * @head: head indices of the circular buffer
- *
- * Return - total number of entries in the circular buffer
- */
-static u32 get_count(struct rvt_rq *rq, u32 tail, u32 head)
-{
- u32 count;
-
- count = head;
-
- if (count >= rq->size)
- count = 0;
- if (count < tail)
- count += rq->size - tail;
- else
- count -= tail;
-
- return count;
-}
-
-/**
* get_rvt_head - get head indices of the circular buffer
* @rq: data structure for request queue entry
* @ip: the QP
@@ -2451,7 +2424,7 @@ int rvt_get_rwqe(struct rvt_qp *qp, bool
if (kwq->count < RVT_RWQ_COUNT_THRESHOLD) {
head = get_rvt_head(rq, ip);
- kwq->count = get_count(rq, tail, head);
+ kwq->count = rvt_get_rq_count(rq, head, tail);
}
if (unlikely(kwq->count == 0)) {
ret = 0;
@@ -2486,7 +2459,9 @@ int rvt_get_rwqe(struct rvt_qp *qp, bool
* the number of remaining WQEs.
*/
if (kwq->count < srq->limit) {
- kwq->count = get_count(rq, tail, get_rvt_head(rq, ip));
+ kwq->count =
+ rvt_get_rq_count(rq,
+ get_rvt_head(rq, ip), tail);
if (kwq->count < srq->limit) {
struct ib_event ev;
--- a/drivers/infiniband/sw/rdmavt/rc.c
+++ b/drivers/infiniband/sw/rdmavt/rc.c
@@ -127,9 +127,7 @@ __be32 rvt_compute_aeth(struct rvt_qp *q
* not atomic, which is OK, since the fuzziness is
* resolved as further ACKs go out.
*/
- credits = head - tail;
- if ((int)credits < 0)
- credits += qp->r_rq.size;
+ credits = rvt_get_rq_count(&qp->r_rq, head, tail);
}
/*
* Binary search the credit table to find the code to
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -278,6 +278,25 @@ struct rvt_rq {
spinlock_t lock ____cacheline_aligned_in_smp;
};
+/**
+ * rvt_get_rq_count - count numbers of request work queue entries
+ * in circular buffer
+ * @rq: data structure for request queue entry
+ * @head: head indices of the circular buffer
+ * @tail: tail indices of the circular buffer
+ *
+ * Return - total number of entries in the Receive Queue
+ */
+
+static inline u32 rvt_get_rq_count(struct rvt_rq *rq, u32 head, u32 tail)
+{
+ u32 count = head - tail;
+
+ if ((s32)count < 0)
+ count += rq->size;
+ return count;
+}
+
/*
* This structure holds the information that the send tasklet needs
* to send a RDMA read response or atomic operation.
Powered by blists - more mailing lists