@@ -86,12 +86,11 @@ int copy_data(struct rxe_pd *pd, int access,
struct rxe_dma_info *dma, void *addr, int length,
enum copy_direction dir, u32 *crcp);
void *iova_to_vaddr(struct rxe_mr *mr, u64 iova, int length);
-struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
- enum lookup_type type);
-int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length);
void rxe_mr_cleanup(struct rxe_pool_entry *arg);
int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
int rxe_invalidate_mr(struct rxe_qp *qp, struct rxe_mr *mr);
+int rxe_mr_check_access(struct rxe_qp *qp, struct rxe_mr *mr,
+ int access, u64 va, u32 resid);
void rxe_mr_cleanup(struct rxe_pool_entry *arg);
/* rxe_mw.c */
@@ -100,6 +99,8 @@ struct ib_mw *rxe_alloc_mw(struct ib_pd *ibpd, enum ib_mw_type type,
int rxe_dealloc_mw(struct ib_mw *ibmw);
int rxe_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe);
int rxe_invalidate_mw(struct rxe_qp *qp, struct rxe_mw *mw);
+int rxe_mw_check_access(struct rxe_qp *qp, struct rxe_mw *mw,
+ int access, u64 va, u32 resid);
void rxe_mw_cleanup(struct rxe_pool_entry *arg);
/* rxe_net.c */
@@ -26,7 +26,7 @@ static void rxe_set_mr_lkey(struct rxe_mr *mr)
pr_err("unable to get random lkey for mr\n");
}
-int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length)
+static int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length)
{
switch (mr->type) {
case RXE_MR_TYPE_DMA:
@@ -385,6 +385,25 @@ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length,
return err;
}
+static struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 lkey)
+{
+ struct rxe_mr *mr;
+ struct rxe_dev *rxe = to_rdev(pd->ibpd.device);
+
+ mr = rxe_pool_get_key(&rxe->mr_pool, &lkey);
+ if (!mr)
+ return NULL;
+
+ if (unlikely((mr->ibmr.lkey != lkey) || (mr->pd != pd) ||
+ (access && !(access & mr->access)) ||
+ (mr->state != RXE_MEM_STATE_VALID))) {
+ rxe_drop_ref(mr);
+ return NULL;
+ }
+
+ return mr;
+}
+
/* copy data in or out of a wqe, i.e. sg list
* under the control of a dma descriptor
*/
@@ -414,7 +433,7 @@ int copy_data(
}
if (sge->length && (offset < sge->length)) {
- mr = lookup_mr(pd, access, sge->lkey, lookup_local);
+ mr = lookup_mr(pd, access, sge->lkey);
if (!mr) {
err = -EINVAL;
goto err1;
@@ -439,8 +458,7 @@ int copy_data(
}
if (sge->length) {
- mr = lookup_mr(pd, access, sge->lkey,
- lookup_local);
+ mr = lookup_mr(pd, access, sge->lkey);
if (!mr) {
err = -EINVAL;
goto err1;
@@ -515,39 +533,39 @@ int advance_dma_data(struct rxe_dma_info *dma, unsigned int length)
return 0;
}
-/* (1) find the mr (mr or mw) corresponding to lkey/rkey
- * depending on lookup_type
- * (2) verify that the (qp) pd matches the mr pd
- * (3) verify that the mr can support the requested access
- * (4) verify that mr state is valid
- */
-struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
- enum lookup_type type)
+/* TODO this needs additional validation */
+int rxe_invalidate_mr(struct rxe_qp *qp, struct rxe_mr *mr)
{
- struct rxe_mr *mr;
- struct rxe_dev *rxe = to_rdev(pd->ibpd.device);
+ mr->state = RXE_MEM_STATE_FREE;
+ return 0;
+}
- mr = rxe_pool_get_key(&rxe->mr_pool, &key);
- if (!mr)
- return NULL;
+int rxe_mr_check_access(struct rxe_qp *qp, struct rxe_mr *mr,
+ int access, u64 va, u32 resid)
+{
+ int ret;
+ struct rxe_pd *pd = to_rpd(mr->ibmr.pd);
- if (unlikely((type == lookup_local && mr->lkey != key) ||
- (type == lookup_remote && mr->rkey != key) ||
- mr->pd != pd ||
- (access && !(access & mr->access)) ||
- mr->state != RXE_MEM_STATE_VALID)) {
- rxe_drop_ref(mr);
- mr = NULL;
+ if (unlikely(mr->state != RXE_MEM_STATE_VALID)) {
+ pr_err("attempt to access a MR that is not in the valid state\n");
+ return -EINVAL;
}
- return mr;
-}
+ /* C10-56 */
+ if (unlikely(pd != qp->pd)) {
+ pr_err("attempt to access a MR with a different PD than the QP\n");
+ return -EINVAL;
+ }
-/* stub for invalidate MR */
-int rxe_invalidate_mr(struct rxe_qp *qp, struct rxe_mr *mr)
-{
- mr->state = RXE_MEM_STATE_FREE;
- return 0;
+ /* C10-57 */
+ if (unlikely(access && !(access & mr->access))) {
+ pr_err("attempt to access a MR without required access rights\n");
+ return -EINVAL;
+ }
+
+ ret = mr_check_range(mr, va, resid);
+
+ return ret;
}
void rxe_mr_cleanup(struct rxe_pool_entry *arg)
@@ -372,6 +372,50 @@ int rxe_invalidate_mw(struct rxe_qp *qp, struct rxe_mw *mw)
return ret;
}
+int rxe_mw_check_access(struct rxe_qp *qp, struct rxe_mw *mw,
+ int access, u64 va, u32 resid)
+{
+ struct rxe_pd *pd = to_rpd(mw->ibmw.pd);
+
+ if (unlikely(mw->state != RXE_MEM_STATE_VALID)) {
+ pr_err_once("attempt to access a MW that is not in the valid state\n");
+ return -EINVAL;
+ }
+
+ /* C10-76.2.1 */
+ if (unlikely((mw->ibmw.type == IB_MW_TYPE_1) && (pd != qp->pd))) {
+ pr_err_once("attempt to access a type 1 MW with a different PD than the QP\n");
+ return -EINVAL;
+ }
+
+ /* o10-37.2.43 */
+ if (unlikely((mw->ibmw.type == IB_MW_TYPE_2) && (mw->qp != qp))) {
+ pr_err_once("attempt to access a type 2 MW that is associated with a different QP\n");
+ return -EINVAL;
+ }
+
+ /* C10-77 */
+ if (unlikely(access && !(access & mw->access))) {
+ pr_err_once("attempt to access a MW without sufficient access\n");
+ return -EINVAL;
+ }
+
+ if (mw->access & IB_ZERO_BASED) {
+ if (unlikely((va + resid) > mw->length)) {
+ pr_err_once("attempt to access a ZB MW out of bounds\n");
+ return -EINVAL;
+ }
+ } else {
+ if (unlikely((va < mw->addr) ||
+ ((va + resid) > (mw->addr + mw->length)))) {
+ pr_err_once("attempt to access a VA MW out of bounds\n");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
void rxe_mw_cleanup(struct rxe_pool_entry *arg)
{
struct rxe_mw *mw = container_of(arg, typeof(*mw), pelem);
@@ -758,8 +758,7 @@ int rxe_requester(void *arg)
again:
/* we come here if we are done with the current wqe but want to
- * get called again. Mostly we loop back to next wqe so should
- * be all one way or the other
+ * get called again.
*/
ret = 0;
goto done;
@@ -392,7 +392,9 @@ static enum resp_states check_length(struct rxe_qp *qp,
static enum resp_states check_rkey(struct rxe_qp *qp,
struct rxe_pkt_info *pkt)
{
- struct rxe_mr *mr = NULL;
+ struct rxe_mr *mr;
+ struct rxe_mw *mw;
+ struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
u64 va;
u32 rkey;
u32 resid;
@@ -400,6 +402,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
int mtu = qp->mtu;
enum resp_states state;
int access;
+ unsigned long flags;
if (pkt->mask & (RXE_READ_MASK | RXE_WRITE_MASK)) {
if (pkt->mask & RXE_RETH_MASK) {
@@ -407,6 +410,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
qp->resp.rkey = reth_rkey(pkt);
qp->resp.resid = reth_len(pkt);
qp->resp.length = reth_len(pkt);
+ qp->resp.offset = 0;
}
access = (pkt->mask & RXE_READ_MASK) ? IB_ACCESS_REMOTE_READ
: IB_ACCESS_REMOTE_WRITE;
@@ -414,6 +418,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
qp->resp.va = atmeth_va(pkt);
qp->resp.rkey = atmeth_rkey(pkt);
qp->resp.resid = sizeof(u64);
+ qp->resp.offset = 0;
access = IB_ACCESS_REMOTE_ATOMIC;
} else {
return RESPST_EXECUTE;
@@ -431,20 +436,46 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
resid = qp->resp.resid;
pktlen = payload_size(pkt);
- mr = lookup_mr(qp->pd, access, rkey, lookup_remote);
- if (!mr) {
- state = RESPST_ERR_RKEY_VIOLATION;
- goto err;
- }
+ /* check rkey on each packet because someone could
+ * have invalidated, deallocated or unregistered it
+ * since the last packet
+ */
+ if (rkey & IS_MW) {
+ mw = rxe_pool_get_key(&rxe->mw_pool, &rkey);
+ if (!mw) {
+ pr_err_once("no MW found with rkey = 0x%08x\n", rkey);
+ state = RESPST_ERR_RKEY_VIOLATION;
+ goto err;
+ }
- if (unlikely(mr->state == RXE_MEM_STATE_FREE)) {
- state = RESPST_ERR_RKEY_VIOLATION;
- goto err;
- }
+ spin_lock_irqsave(&mw->lock, flags);
+ if (rxe_mw_check_access(qp, mw, access, va, resid)) {
+ spin_unlock_irqrestore(&mw->lock, flags);
+ rxe_drop_ref(mw);
+ state = RESPST_ERR_RKEY_VIOLATION;
+ goto err;
+ }
+
+ mr = mw->mr;
+ rxe_add_ref(mr);
- if (mr_check_range(mr, va, resid)) {
- state = RESPST_ERR_RKEY_VIOLATION;
- goto err;
+ if (mw->access & IB_ZERO_BASED)
+ qp->resp.offset = mw->addr;
+
+ spin_unlock_irqrestore(&mw->lock, flags);
+ rxe_drop_ref(mw);
+ } else {
+ mr = rxe_pool_get_key(&rxe->mr_pool, &rkey);
+ if (!mr || (mr->rkey != rkey)) {
+ pr_err_once("no MR found with rkey = 0x%08x\n", rkey);
+ state = RESPST_ERR_RKEY_VIOLATION;
+ goto err;
+ }
+
+ if (rxe_mr_check_access(qp, mr, access, va, resid)) {
+ state = RESPST_ERR_RKEY_VIOLATION;
+ goto err;
+ }
}
if (pkt->mask & RXE_WRITE_MASK) {
@@ -500,8 +531,8 @@ static enum resp_states write_data_in(struct rxe_qp *qp,
int err;
int data_len = payload_size(pkt);
- err = rxe_mr_copy(qp->resp.mr, qp->resp.va, payload_addr(pkt),
- data_len, to_mr_obj, NULL);
+ err = rxe_mr_copy(qp->resp.mr, qp->resp.va + qp->resp.offset,
+ payload_addr(pkt), data_len, to_mr_obj, NULL);
if (err) {
rc = RESPST_ERR_RKEY_VIOLATION;
goto out;
@@ -520,7 +551,6 @@ static DEFINE_SPINLOCK(atomic_ops_lock);
static enum resp_states process_atomic(struct rxe_qp *qp,
struct rxe_pkt_info *pkt)
{
- u64 iova = atmeth_va(pkt);
u64 *vaddr;
enum resp_states ret;
struct rxe_mr *mr = qp->resp.mr;
@@ -530,7 +560,7 @@ static enum resp_states process_atomic(struct rxe_qp *qp,
goto out;
}
- vaddr = iova_to_vaddr(mr, iova, sizeof(u64));
+ vaddr = iova_to_vaddr(mr, qp->resp.va + qp->resp.offset, sizeof(u64));
/* check vaddr is 8 bytes aligned. */
if (!vaddr || (uintptr_t)vaddr & 7) {
@@ -655,8 +685,10 @@ static enum resp_states read_reply(struct rxe_qp *qp,
res->type = RXE_READ_MASK;
res->replay = 0;
- res->read.va = qp->resp.va;
- res->read.va_org = qp->resp.va;
+ res->read.va = qp->resp.va +
+ qp->resp.offset;
+ res->read.va_org = qp->resp.va +
+ qp->resp.offset;
res->first_psn = req_pkt->psn;
@@ -185,6 +185,7 @@ struct rxe_resp_info {
/* RDMA read / atomic only */
u64 va;
+ u64 offset;
struct rxe_mr *mr;
u32 resid;
u32 rkey;
Extended current support for rkeys referencing MRs to include rkeys referencing MWs. Signed-off-by: Bob Pearson <rpearson@hpe.com> --- drivers/infiniband/sw/rxe/rxe_loc.h | 7 ++- drivers/infiniband/sw/rxe/rxe_mr.c | 80 ++++++++++++++++----------- drivers/infiniband/sw/rxe/rxe_mw.c | 44 +++++++++++++++ drivers/infiniband/sw/rxe/rxe_req.c | 3 +- drivers/infiniband/sw/rxe/rxe_resp.c | 70 ++++++++++++++++------- drivers/infiniband/sw/rxe/rxe_verbs.h | 1 + 6 files changed, 150 insertions(+), 55 deletions(-)