IB/hfi1: Optimize lkey validation structures

Profiling shows that the key validation is susceptible
to cache line trading when accessing the lkey table.

Fix by separating out the read mostly fields from the write
fields.   In addition the shift amount, which is function
of the lkey table size, is precomputed and stored with the
table pointer.   Since both the shift and table pointer
are in the same read mostly cacheline, this saves a cache
line in this hot path.

Reviewed-by: Sebastian Sanchez <sebastian.sanchez@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c
index 46b64970058ece11bf3c272ca5fb80d3c1cabff6..4acf179adf3b8768b7b25e7032ef0e1c8f310baf 100644 (file)
--- a/drivers/infiniband/sw/rdmavt/mr.c
+++ b/drivers/infiniband/sw/rdmavt/mr.c
@@ -84,6 +84,7 @@ int rvt_driver_mr_init(struct rvt_dev_info *rdi)
                lkey_table_size = rdi->dparms.lkey_table_size;
        }
        rdi->lkey_table.max = 1 << lkey_table_size;
+       rdi->lkey_table.shift = 32 - lkey_table_size;
        lk_tab_size = rdi->lkey_table.max * sizeof(*rdi->lkey_table.table);
        rdi->lkey_table.table = (struct rvt_mregion __rcu **)
                               vmalloc_node(lk_tab_size, rdi->dparms.node);
@@ -774,7 +775,6 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
        struct rvt_mregion *mr;
        unsigned n, m;
        size_t off;
-       struct rvt_dev_info *dev = ib_to_rvt(pd->ibpd.device);
 
        /*
         * We use LKEY == zero for kernel virtual addresses
@@ -782,6 +782,8 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
         */
        rcu_read_lock();
        if (sge->lkey == 0) {
+               struct rvt_dev_info *dev = ib_to_rvt(pd->ibpd.device);
+
                if (pd->user)
                        goto bail;
                mr = rcu_dereference(dev->dma_mr);
@@ -798,8 +800,7 @@ int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
                isge->n = 0;
                goto ok;
        }
-       mr = rcu_dereference(
-               rkt->table[(sge->lkey >> (32 - dev->dparms.lkey_table_size))]);
+       mr = rcu_dereference(rkt->table[sge->lkey >> rkt->shift]);
        if (unlikely(!mr || atomic_read(&mr->lkey_invalid) ||
                     mr->lkey != sge->lkey || mr->pd != &pd->ibpd))
                goto bail;
@@ -899,8 +900,7 @@ int rvt_rkey_ok(struct rvt_qp *qp, struct rvt_sge *sge,
                goto ok;
        }
 
-       mr = rcu_dereference(
-               rkt->table[(rkey >> (32 - dev->dparms.lkey_table_size))]);
+       mr = rcu_dereference(rkt->table[rkey >> rkt->shift]);
        if (unlikely(!mr || atomic_read(&mr->lkey_invalid) ||
                     mr->lkey != rkey || qp->ibqp.pd != mr->pd))
                goto bail;

diff --git a/include/rdma/rdmavt_mr.h b/include/rdma/rdmavt_mr.h
index 6b3c6c8b6b772a1774012d5b4f32b827a03f5537..de59de28b6a2ae8f25927c1d92dc2d63e02a1c45 100644 (file)
--- a/include/rdma/rdmavt_mr.h
+++ b/include/rdma/rdmavt_mr.h
@@ -90,11 +90,15 @@ struct rvt_mregion {
 #define RVT_MAX_LKEY_TABLE_BITS 23
 
 struct rvt_lkey_table {
-       spinlock_t lock; /* protect changes in this struct */
-       u32 next;               /* next unused index (speeds search) */
-       u32 gen;                /* generation count */
+       /* read mostly fields */
        u32 max;                /* size of the table */
+       u32 shift;              /* lkey/rkey shift */
        struct rvt_mregion __rcu **table;
+       /* writeable fields */
+       /* protect changes in this struct */
+       spinlock_t lock ____cacheline_aligned_in_smp;
+       u32 next;               /* next unused index (speeds search) */
+       u32 gen;                /* generation count */
 };
 
 /*