From 8d91c1e411f55d7ea91b1183a2e9f8088fb4d5be Mon Sep 17 00:00:00 2001 From: André Fabian Silva Delgado Date: Tue, 15 Dec 2015 14:52:16 -0300 Subject: Linux-libre 4.3.2-gnu --- .../staging/lustre/lnet/klnds/o2iblnd/o2iblnd.c | 265 +-------------------- .../staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h | 146 +++++------- .../staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c | 58 +---- .../lustre/lnet/klnds/o2iblnd/o2iblnd_modparams.c | 6 - 4 files changed, 78 insertions(+), 397 deletions(-) (limited to 'drivers/staging/lustre/lnet/klnds/o2iblnd') diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.c index 4eb24a11b..c29d2ced2 100644 --- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.c +++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.c @@ -1390,7 +1390,7 @@ static int kiblnd_create_fmr_pool(kib_fmr_poolset_t *fps, .max_pages_per_fmr = LNET_MAX_PAYLOAD/PAGE_SIZE, .page_shift = PAGE_SHIFT, .access = (IB_ACCESS_LOCAL_WRITE | - IB_ACCESS_REMOTE_WRITE), + IB_ACCESS_REMOTE_WRITE), .pool_size = fps->fps_pool_size, .dirty_watermark = fps->fps_flush_trigger, .flush_function = NULL, @@ -1789,140 +1789,6 @@ struct list_head *kiblnd_pool_alloc_node(kib_poolset_t *ps) goto again; } -void kiblnd_pmr_pool_unmap(kib_phys_mr_t *pmr) -{ - kib_pmr_pool_t *ppo = pmr->pmr_pool; - struct ib_mr *mr = pmr->pmr_mr; - - pmr->pmr_mr = NULL; - kiblnd_pool_free_node(&ppo->ppo_pool, &pmr->pmr_list); - if (mr != NULL) - ib_dereg_mr(mr); -} - -int kiblnd_pmr_pool_map(kib_pmr_poolset_t *pps, kib_hca_dev_t *hdev, - kib_rdma_desc_t *rd, __u64 *iova, kib_phys_mr_t **pp_pmr) -{ - kib_phys_mr_t *pmr; - struct list_head *node; - int rc; - int i; - - node = kiblnd_pool_alloc_node(&pps->pps_poolset); - if (node == NULL) { - CERROR("Failed to allocate PMR descriptor\n"); - return -ENOMEM; - } - - pmr = container_of(node, kib_phys_mr_t, pmr_list); - if (pmr->pmr_pool->ppo_hdev != hdev) { - kiblnd_pool_free_node(&pmr->pmr_pool->ppo_pool, node); - return -EAGAIN; - } - - for (i = 0; i < rd->rd_nfrags; i++) { - pmr->pmr_ipb[i].addr = rd->rd_frags[i].rf_addr; - pmr->pmr_ipb[i].size = rd->rd_frags[i].rf_nob; - } - - pmr->pmr_mr = ib_reg_phys_mr(hdev->ibh_pd, - pmr->pmr_ipb, rd->rd_nfrags, - IB_ACCESS_LOCAL_WRITE | - IB_ACCESS_REMOTE_WRITE, - iova); - if (!IS_ERR(pmr->pmr_mr)) { - pmr->pmr_iova = *iova; - *pp_pmr = pmr; - return 0; - } - - rc = PTR_ERR(pmr->pmr_mr); - CERROR("Failed ib_reg_phys_mr: %d\n", rc); - - pmr->pmr_mr = NULL; - kiblnd_pool_free_node(&pmr->pmr_pool->ppo_pool, node); - - return rc; -} - -static void kiblnd_destroy_pmr_pool(kib_pool_t *pool) -{ - kib_pmr_pool_t *ppo = container_of(pool, kib_pmr_pool_t, ppo_pool); - kib_phys_mr_t *pmr; - kib_phys_mr_t *tmp; - - LASSERT(pool->po_allocated == 0); - - list_for_each_entry_safe(pmr, tmp, &pool->po_free_list, pmr_list) { - LASSERT(pmr->pmr_mr == NULL); - list_del(&pmr->pmr_list); - - if (pmr->pmr_ipb != NULL) { - LIBCFS_FREE(pmr->pmr_ipb, - IBLND_MAX_RDMA_FRAGS * - sizeof(struct ib_phys_buf)); - } - - LIBCFS_FREE(pmr, sizeof(kib_phys_mr_t)); - } - - kiblnd_fini_pool(pool); - if (ppo->ppo_hdev != NULL) - kiblnd_hdev_decref(ppo->ppo_hdev); - - LIBCFS_FREE(ppo, sizeof(kib_pmr_pool_t)); -} - -static inline int kiblnd_pmr_pool_size(int ncpts) -{ - int size = *kiblnd_tunables.kib_pmr_pool_size / ncpts; - - return max(IBLND_PMR_POOL, size); -} - -static int kiblnd_create_pmr_pool(kib_poolset_t *ps, int size, - kib_pool_t **pp_po) -{ - struct kib_pmr_pool *ppo; - struct kib_pool *pool; - kib_phys_mr_t *pmr; - int i; - - LIBCFS_CPT_ALLOC(ppo, lnet_cpt_table(), - ps->ps_cpt, sizeof(kib_pmr_pool_t)); - if (ppo == NULL) { - CERROR("Failed to allocate PMR pool\n"); - return -ENOMEM; - } - - pool = &ppo->ppo_pool; - kiblnd_init_pool(ps, pool, size); - - for (i = 0; i < size; i++) { - LIBCFS_CPT_ALLOC(pmr, lnet_cpt_table(), - ps->ps_cpt, sizeof(kib_phys_mr_t)); - if (pmr == NULL) - break; - - pmr->pmr_pool = ppo; - LIBCFS_CPT_ALLOC(pmr->pmr_ipb, lnet_cpt_table(), ps->ps_cpt, - IBLND_MAX_RDMA_FRAGS * sizeof(*pmr->pmr_ipb)); - if (pmr->pmr_ipb == NULL) - break; - - list_add(&pmr->pmr_list, &pool->po_free_list); - } - - if (i < size) { - ps->ps_pool_destroy(pool); - return -ENOMEM; - } - - ppo->ppo_hdev = kiblnd_current_hdev(ps->ps_net->ibn_dev); - *pp_po = pool; - return 0; -} - static void kiblnd_destroy_tx_pool(kib_pool_t *pool) { kib_tx_pool_t *tpo = container_of(pool, kib_tx_pool_t, tpo_pool); @@ -2078,7 +1944,6 @@ static void kiblnd_net_fini_pools(kib_net_t *net) cfs_cpt_for_each(i, lnet_cpt_table()) { kib_tx_poolset_t *tps; kib_fmr_poolset_t *fps; - kib_pmr_poolset_t *pps; if (net->ibn_tx_ps != NULL) { tps = net->ibn_tx_ps[i]; @@ -2089,11 +1954,6 @@ static void kiblnd_net_fini_pools(kib_net_t *net) fps = net->ibn_fmr_ps[i]; kiblnd_fini_fmr_poolset(fps); } - - if (net->ibn_pmr_ps != NULL) { - pps = net->ibn_pmr_ps[i]; - kiblnd_fini_poolset(&pps->pps_poolset); - } } if (net->ibn_tx_ps != NULL) { @@ -2105,18 +1965,13 @@ static void kiblnd_net_fini_pools(kib_net_t *net) cfs_percpt_free(net->ibn_fmr_ps); net->ibn_fmr_ps = NULL; } - - if (net->ibn_pmr_ps != NULL) { - cfs_percpt_free(net->ibn_pmr_ps); - net->ibn_pmr_ps = NULL; - } } static int kiblnd_net_init_pools(kib_net_t *net, __u32 *cpts, int ncpts) { unsigned long flags; int cpt; - int rc; + int rc = 0; int i; read_lock_irqsave(&kiblnd_data.kib_global_lock, flags); @@ -2137,12 +1992,16 @@ static int kiblnd_net_init_pools(kib_net_t *net, __u32 *cpts, int ncpts) goto failed; } - /* TX pool must be created later than FMR/PMR, see LU-2268 - * for details */ + /* + * TX pool must be created later than FMR, see LU-2268 + * for details + */ LASSERT(net->ibn_tx_ps == NULL); - /* premapping can fail if ibd_nmr > 1, so we always create - * FMR/PMR pool and map-on-demand if premapping failed */ + /* + * premapping can fail if ibd_nmr > 1, so we always create + * FMR pool and map-on-demand if premapping failed + */ net->ibn_fmr_ps = cfs_percpt_alloc(lnet_cpt_table(), sizeof(kib_fmr_poolset_t)); @@ -2158,7 +2017,7 @@ static int kiblnd_net_init_pools(kib_net_t *net, __u32 *cpts, int ncpts) kiblnd_fmr_pool_size(ncpts), kiblnd_fmr_flush_trigger(ncpts)); if (rc == -ENOSYS && i == 0) /* no FMR */ - break; /* create PMR pool */ + break; if (rc != 0) { /* a real error */ CERROR("Can't initialize FMR pool for CPT %d: %d\n", @@ -2175,38 +2034,8 @@ static int kiblnd_net_init_pools(kib_net_t *net, __u32 *cpts, int ncpts) cfs_percpt_free(net->ibn_fmr_ps); net->ibn_fmr_ps = NULL; - CWARN("Device does not support FMR, failing back to PMR\n"); - - if (*kiblnd_tunables.kib_pmr_pool_size < - *kiblnd_tunables.kib_ntx / 4) { - CERROR("Can't set pmr pool size (%d) < ntx / 4(%d)\n", - *kiblnd_tunables.kib_pmr_pool_size, - *kiblnd_tunables.kib_ntx / 4); - rc = -EINVAL; - goto failed; - } - - net->ibn_pmr_ps = cfs_percpt_alloc(lnet_cpt_table(), - sizeof(kib_pmr_poolset_t)); - if (net->ibn_pmr_ps == NULL) { - CERROR("Failed to allocate PMR pool array\n"); - rc = -ENOMEM; - goto failed; - } - - for (i = 0; i < ncpts; i++) { - cpt = (cpts == NULL) ? i : cpts[i]; - rc = kiblnd_init_poolset(&net->ibn_pmr_ps[cpt]->pps_poolset, - cpt, net, "PMR", - kiblnd_pmr_pool_size(ncpts), - kiblnd_create_pmr_pool, - kiblnd_destroy_pmr_pool, NULL, NULL); - if (rc != 0) { - CERROR("Can't initialize PMR pool for CPT %d: %d\n", - cpt, rc); + CWARN("Device does not support FMR\n"); goto failed; - } - } create_tx_pool: net->ibn_tx_ps = cfs_percpt_alloc(lnet_cpt_table(), @@ -2318,17 +2147,13 @@ void kiblnd_hdev_destroy(kib_hca_dev_t *hdev) static int kiblnd_hdev_setup_mrs(kib_hca_dev_t *hdev) { struct ib_mr *mr; - int i; int rc; - __u64 mm_size; - __u64 mr_size; int acflags = IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE; rc = kiblnd_hdev_get_attr(hdev); if (rc != 0) return rc; - if (hdev->ibh_mr_shift == 64) { LIBCFS_ALLOC(hdev->ibh_mrs, 1 * sizeof(*hdev->ibh_mrs)); if (hdev->ibh_mrs == NULL) { CERROR("Failed to allocate MRs table\n"); @@ -2347,53 +2172,6 @@ static int kiblnd_hdev_setup_mrs(kib_hca_dev_t *hdev) hdev->ibh_mrs[0] = mr; - goto out; - } - - mr_size = 1ULL << hdev->ibh_mr_shift; - mm_size = (unsigned long)high_memory - PAGE_OFFSET; - - hdev->ibh_nmrs = (int)((mm_size + mr_size - 1) >> hdev->ibh_mr_shift); - - if (hdev->ibh_mr_shift < 32 || hdev->ibh_nmrs > 1024) { - /* it's 4T..., assume we will re-code at that time */ - CERROR("Can't support memory size: x%#llx with MR size: x%#llx\n", - mm_size, mr_size); - return -EINVAL; - } - - /* create an array of MRs to cover all memory */ - LIBCFS_ALLOC(hdev->ibh_mrs, sizeof(*hdev->ibh_mrs) * hdev->ibh_nmrs); - if (hdev->ibh_mrs == NULL) { - CERROR("Failed to allocate MRs' table\n"); - return -ENOMEM; - } - - for (i = 0; i < hdev->ibh_nmrs; i++) { - struct ib_phys_buf ipb; - __u64 iova; - - ipb.size = hdev->ibh_mr_size; - ipb.addr = i * mr_size; - iova = ipb.addr; - - mr = ib_reg_phys_mr(hdev->ibh_pd, &ipb, 1, acflags, &iova); - if (IS_ERR(mr)) { - CERROR("Failed ib_reg_phys_mr addr %#llx size %#llx : %ld\n", - ipb.addr, ipb.size, PTR_ERR(mr)); - kiblnd_hdev_cleanup_mrs(hdev); - return PTR_ERR(mr); - } - - LASSERT(iova == ipb.addr); - - hdev->ibh_mrs[i] = mr; - } - -out: - if (hdev->ibh_mr_size != ~0ULL || hdev->ibh_nmrs != 1) - LCONSOLE_INFO("Register global MR array, MR size: %#llx, array size: %d\n", - hdev->ibh_mr_size, hdev->ibh_nmrs); return 0; } @@ -2564,14 +2342,9 @@ int kiblnd_dev_failover(kib_dev_t *dev) kiblnd_fail_poolset(&net->ibn_tx_ps[i]->tps_poolset, &zombie_tpo); - if (net->ibn_fmr_ps != NULL) { + if (net->ibn_fmr_ps) kiblnd_fail_fmr_poolset(net->ibn_fmr_ps[i], &zombie_fpo); - - } else if (net->ibn_pmr_ps != NULL) { - kiblnd_fail_poolset(&net->ibn_pmr_ps[i]-> - pps_poolset, &zombie_ppo); - } } } @@ -2667,9 +2440,6 @@ static void kiblnd_base_shutdown(void) LASSERT(list_empty(&kiblnd_data.kib_devs)); - CDEBUG(D_MALLOC, "before LND base cleanup: kmem %d\n", - atomic_read(&libcfs_kmemory)); - switch (kiblnd_data.kib_init) { default: LBUG(); @@ -2720,9 +2490,6 @@ static void kiblnd_base_shutdown(void) if (kiblnd_data.kib_scheds != NULL) cfs_percpt_free(kiblnd_data.kib_scheds); - CDEBUG(D_MALLOC, "after LND base cleanup: kmem %d\n", - atomic_read(&libcfs_kmemory)); - kiblnd_data.kib_init = IBLND_INIT_NOTHING; module_put(THIS_MODULE); } @@ -2739,9 +2506,6 @@ void kiblnd_shutdown(lnet_ni_t *ni) if (net == NULL) goto out; - CDEBUG(D_MALLOC, "before LND net cleanup: kmem %d\n", - atomic_read(&libcfs_kmemory)); - write_lock_irqsave(g_lock, flags); net->ibn_shutdown = 1; write_unlock_irqrestore(g_lock, flags); @@ -2786,9 +2550,6 @@ void kiblnd_shutdown(lnet_ni_t *ni) break; } - CDEBUG(D_MALLOC, "after LND net cleanup: kmem %d\n", - atomic_read(&libcfs_kmemory)); - net->ibn_init = IBLND_INIT_NOTHING; ni->ni_data = NULL; diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h index f5d1d9f8f..f4b6c33ac 100644 --- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h +++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h @@ -48,7 +48,7 @@ #include #include -#include +#include #include #include @@ -104,7 +104,6 @@ typedef struct { int *kib_map_on_demand; /* map-on-demand if RD has more * fragments than this value, 0 * disable map-on-demand */ - int *kib_pmr_pool_size; /* # physical MR in pool */ int *kib_fmr_pool_size; /* # FMRs in pool */ int *kib_fmr_flush_trigger; /* When to trigger FMR flush */ int *kib_fmr_cache; /* enable FMR pool cache? */ @@ -120,7 +119,7 @@ extern kib_tunables_t kiblnd_tunables; #define IBLND_CREDIT_HIGHWATER_V1 7 /* V1 only : when eagerly to return credits */ #define IBLND_CREDITS_DEFAULT 8 /* default # of peer credits */ -#define IBLND_CREDITS_MAX ((typeof(((kib_msg_t*) 0)->ibm_credits)) - 1) /* Max # of peer credits */ +#define IBLND_CREDITS_MAX ((typeof(((kib_msg_t *) 0)->ibm_credits)) - 1) /* Max # of peer credits */ #define IBLND_MSG_QUEUE_SIZE(v) ((v) == IBLND_MSG_VERSION_1 ? \ IBLND_MSG_QUEUE_SIZE_V1 : \ @@ -163,7 +162,6 @@ kiblnd_concurrent_sends_v1(void) /* Pools (shared by connections on each CPT) */ /* These pools can grow at runtime, so don't need give a very large value */ #define IBLND_TX_POOL 256 -#define IBLND_PMR_POOL 256 #define IBLND_FMR_POOL 256 #define IBLND_FMR_POOL_FLUSH 192 @@ -232,17 +230,6 @@ typedef struct { struct page *ibp_pages[0]; /* page array */ } kib_pages_t; -struct kib_pmr_pool; - -typedef struct { - struct list_head pmr_list; /* chain node */ - struct ib_phys_buf *pmr_ipb; /* physical buffer */ - struct ib_mr *pmr_mr; /* IB MR */ - struct kib_pmr_pool *pmr_pool; /* owner of this MR */ - __u64 pmr_iova; /* Virtual I/O address */ - int pmr_refcount; /* reference count */ -} kib_phys_mr_t; - struct kib_pool; struct kib_poolset; @@ -298,15 +285,6 @@ typedef struct { kib_pages_t *tpo_tx_pages; /* premapped tx msg pages */ } kib_tx_pool_t; -typedef struct { - kib_poolset_t pps_poolset; /* pool-set */ -} kib_pmr_poolset_t; - -typedef struct kib_pmr_pool { - struct kib_hca_dev *ppo_hdev; /* device for this pool */ - kib_pool_t ppo_pool; /* pool */ -} kib_pmr_pool_t; - typedef struct { spinlock_t fps_lock; /* serialize */ struct kib_net *fps_net; /* IB network */ @@ -347,7 +325,6 @@ typedef struct kib_net { kib_tx_poolset_t **ibn_tx_ps; /* tx pool-set */ kib_fmr_poolset_t **ibn_fmr_ps; /* fmr pool-set */ - kib_pmr_poolset_t **ibn_pmr_ps; /* pmr pool-set */ kib_dev_t *ibn_dev; /* underlying IB device */ } kib_net_t; @@ -519,7 +496,7 @@ typedef struct kib_rx /* receive message */ enum ib_wc_status rx_status; /* completion status */ kib_msg_t *rx_msg; /* message buffer (host vaddr) */ __u64 rx_msgaddr; /* message buffer (I/O addr) */ - DECLARE_PCI_UNMAP_ADDR (rx_msgunmap); /* for dma_unmap_single() */ + DECLARE_PCI_UNMAP_ADDR(rx_msgunmap); /* for dma_unmap_single() */ struct ib_recv_wr rx_wrq; /* receive work item... */ struct ib_sge rx_sge; /* ...and its memory */ } kib_rx_t; @@ -546,7 +523,7 @@ typedef struct kib_tx /* transmit message */ * completion */ kib_msg_t *tx_msg; /* message buffer (host vaddr) */ __u64 tx_msgaddr; /* message buffer (I/O addr) */ - DECLARE_PCI_UNMAP_ADDR (tx_msgunmap); /* for dma_unmap_single() */ + DECLARE_PCI_UNMAP_ADDR(tx_msgunmap); /* for dma_unmap_single() */ int tx_nwrq; /* # send work items */ struct ib_send_wr *tx_wrq; /* send work items... */ struct ib_sge *tx_sge; /* ...and their memory */ @@ -554,10 +531,7 @@ typedef struct kib_tx /* transmit message */ int tx_nfrags; /* # entries in... */ struct scatterlist *tx_frags; /* dma_map_sg descriptor */ __u64 *tx_pages; /* rdma phys page addrs */ - union { - kib_phys_mr_t *pmr; /* MR for physical buffer */ - kib_fmr_t fmr; /* FMR */ - } tx_u; + kib_fmr_t fmr; /* FMR */ int tx_dmadir; /* dma direction */ } kib_tx_t; @@ -642,19 +616,19 @@ typedef struct kib_peer { extern kib_data_t kiblnd_data; -extern void kiblnd_hdev_destroy(kib_hca_dev_t *hdev); +void kiblnd_hdev_destroy(kib_hca_dev_t *hdev); static inline void kiblnd_hdev_addref_locked(kib_hca_dev_t *hdev) { - LASSERT (atomic_read(&hdev->ibh_ref) > 0); + LASSERT(atomic_read(&hdev->ibh_ref) > 0); atomic_inc(&hdev->ibh_ref); } static inline void kiblnd_hdev_decref(kib_hca_dev_t *hdev) { - LASSERT (atomic_read(&hdev->ibh_ref) > 0); + LASSERT(atomic_read(&hdev->ibh_ref) > 0); if (atomic_dec_and_test(&hdev->ibh_ref)) kiblnd_hdev_destroy(hdev); } @@ -701,7 +675,7 @@ do { \ do { \ CDEBUG(D_NET, "peer[%p] -> %s (%d)++\n", \ (peer), libcfs_nid2str((peer)->ibp_nid), \ - atomic_read (&(peer)->ibp_refcount)); \ + atomic_read(&(peer)->ibp_refcount)); \ atomic_inc(&(peer)->ibp_refcount); \ } while (0) @@ -709,32 +683,32 @@ do { \ do { \ CDEBUG(D_NET, "peer[%p] -> %s (%d)--\n", \ (peer), libcfs_nid2str((peer)->ibp_nid), \ - atomic_read (&(peer)->ibp_refcount)); \ + atomic_read(&(peer)->ibp_refcount)); \ LASSERT_ATOMIC_POS(&(peer)->ibp_refcount); \ if (atomic_dec_and_test(&(peer)->ibp_refcount)) \ kiblnd_destroy_peer(peer); \ } while (0) static inline struct list_head * -kiblnd_nid2peerlist (lnet_nid_t nid) +kiblnd_nid2peerlist(lnet_nid_t nid) { unsigned int hash = ((unsigned int)nid) % kiblnd_data.kib_peer_hash_size; - return (&kiblnd_data.kib_peers [hash]); + return &kiblnd_data.kib_peers[hash]; } static inline int -kiblnd_peer_active (kib_peer_t *peer) +kiblnd_peer_active(kib_peer_t *peer) { /* Am I in the peer hash table? */ - return (!list_empty(&peer->ibp_list)); + return !list_empty(&peer->ibp_list); } static inline kib_conn_t * -kiblnd_get_conn_locked (kib_peer_t *peer) +kiblnd_get_conn_locked(kib_peer_t *peer) { - LASSERT (!list_empty(&peer->ibp_conns)); + LASSERT(!list_empty(&peer->ibp_conns)); /* just return the first connection */ return list_entry(peer->ibp_conns.next, kib_conn_t, ibc_list); @@ -751,7 +725,7 @@ kiblnd_send_keepalive(kib_conn_t *conn) static inline int kiblnd_need_noop(kib_conn_t *conn) { - LASSERT (conn->ibc_state >= IBLND_CONN_ESTABLISHED); + LASSERT(conn->ibc_state >= IBLND_CONN_ESTABLISHED); if (conn->ibc_outstanding_credits < IBLND_CREDITS_HIGHWATER(conn->ibc_version) && @@ -788,7 +762,7 @@ kiblnd_abort_receives(kib_conn_t *conn) } static inline const char * -kiblnd_queue2str (kib_conn_t *conn, struct list_head *q) +kiblnd_queue2str(kib_conn_t *conn, struct list_head *q) { if (q == &conn->ibc_tx_queue) return "tx_queue"; @@ -815,43 +789,43 @@ kiblnd_queue2str (kib_conn_t *conn, struct list_head *q) #define IBLND_WID_MASK 3UL static inline __u64 -kiblnd_ptr2wreqid (void *ptr, int type) +kiblnd_ptr2wreqid(void *ptr, int type) { unsigned long lptr = (unsigned long)ptr; - LASSERT ((lptr & IBLND_WID_MASK) == 0); - LASSERT ((type & ~IBLND_WID_MASK) == 0); + LASSERT((lptr & IBLND_WID_MASK) == 0); + LASSERT((type & ~IBLND_WID_MASK) == 0); return (__u64)(lptr | type); } static inline void * -kiblnd_wreqid2ptr (__u64 wreqid) +kiblnd_wreqid2ptr(__u64 wreqid) { return (void *)(((unsigned long)wreqid) & ~IBLND_WID_MASK); } static inline int -kiblnd_wreqid2type (__u64 wreqid) +kiblnd_wreqid2type(__u64 wreqid) { - return (wreqid & IBLND_WID_MASK); + return wreqid & IBLND_WID_MASK; } static inline void -kiblnd_set_conn_state (kib_conn_t *conn, int state) +kiblnd_set_conn_state(kib_conn_t *conn, int state) { conn->ibc_state = state; mb(); } static inline void -kiblnd_init_msg (kib_msg_t *msg, int type, int body_nob) +kiblnd_init_msg(kib_msg_t *msg, int type, int body_nob) { msg->ibm_type = type; msg->ibm_nob = offsetof(kib_msg_t, ibm_u) + body_nob; } static inline int -kiblnd_rd_size (kib_rdma_desc_t *rd) +kiblnd_rd_size(kib_rdma_desc_t *rd) { int i; int size; @@ -887,7 +861,7 @@ kiblnd_rd_consume_frag(kib_rdma_desc_t *rd, int index, __u32 nob) rd->rd_frags[index].rf_addr += nob; rd->rd_frags[index].rf_nob -= nob; } else { - index ++; + index++; } return index; @@ -896,8 +870,8 @@ kiblnd_rd_consume_frag(kib_rdma_desc_t *rd, int index, __u32 nob) static inline int kiblnd_rd_msg_size(kib_rdma_desc_t *rd, int msgtype, int n) { - LASSERT (msgtype == IBLND_MSG_GET_REQ || - msgtype == IBLND_MSG_PUT_ACK); + LASSERT(msgtype == IBLND_MSG_GET_REQ || + msgtype == IBLND_MSG_PUT_ACK); return msgtype == IBLND_MSG_GET_REQ ? offsetof(kib_get_msg_t, ibgm_rd.rd_frags[n]) : @@ -978,57 +952,53 @@ int kiblnd_fmr_pool_map(kib_fmr_poolset_t *fps, __u64 *pages, int npages, __u64 iov, kib_fmr_t *fmr); void kiblnd_fmr_pool_unmap(kib_fmr_t *fmr, int status); -int kiblnd_pmr_pool_map(kib_pmr_poolset_t *pps, kib_hca_dev_t *hdev, - kib_rdma_desc_t *rd, __u64 *iova, kib_phys_mr_t **pp_pmr); -void kiblnd_pmr_pool_unmap(kib_phys_mr_t *pmr); - -int kiblnd_startup (lnet_ni_t *ni); -void kiblnd_shutdown (lnet_ni_t *ni); -int kiblnd_ctl (lnet_ni_t *ni, unsigned int cmd, void *arg); -void kiblnd_query (struct lnet_ni *ni, lnet_nid_t nid, unsigned long *when); +int kiblnd_startup(lnet_ni_t *ni); +void kiblnd_shutdown(lnet_ni_t *ni); +int kiblnd_ctl(lnet_ni_t *ni, unsigned int cmd, void *arg); +void kiblnd_query(struct lnet_ni *ni, lnet_nid_t nid, unsigned long *when); int kiblnd_tunables_init(void); void kiblnd_tunables_fini(void); -int kiblnd_connd (void *arg); +int kiblnd_connd(void *arg); int kiblnd_scheduler(void *arg); int kiblnd_thread_start(int (*fn)(void *arg), void *arg, char *name); -int kiblnd_failover_thread (void *arg); +int kiblnd_failover_thread(void *arg); int kiblnd_alloc_pages(kib_pages_t **pp, int cpt, int npages); -void kiblnd_free_pages (kib_pages_t *p); +void kiblnd_free_pages(kib_pages_t *p); int kiblnd_cm_callback(struct rdma_cm_id *cmid, struct rdma_cm_event *event); int kiblnd_translate_mtu(int value); int kiblnd_dev_failover(kib_dev_t *dev); -int kiblnd_create_peer (lnet_ni_t *ni, kib_peer_t **peerp, lnet_nid_t nid); -void kiblnd_destroy_peer (kib_peer_t *peer); -void kiblnd_destroy_dev (kib_dev_t *dev); -void kiblnd_unlink_peer_locked (kib_peer_t *peer); -void kiblnd_peer_alive (kib_peer_t *peer); -kib_peer_t *kiblnd_find_peer_locked (lnet_nid_t nid); -void kiblnd_peer_connect_failed (kib_peer_t *peer, int active, int error); -int kiblnd_close_stale_conns_locked (kib_peer_t *peer, +int kiblnd_create_peer(lnet_ni_t *ni, kib_peer_t **peerp, lnet_nid_t nid); +void kiblnd_destroy_peer(kib_peer_t *peer); +void kiblnd_destroy_dev(kib_dev_t *dev); +void kiblnd_unlink_peer_locked(kib_peer_t *peer); +void kiblnd_peer_alive(kib_peer_t *peer); +kib_peer_t *kiblnd_find_peer_locked(lnet_nid_t nid); +void kiblnd_peer_connect_failed(kib_peer_t *peer, int active, int error); +int kiblnd_close_stale_conns_locked(kib_peer_t *peer, int version, __u64 incarnation); -int kiblnd_close_peer_conns_locked (kib_peer_t *peer, int why); +int kiblnd_close_peer_conns_locked(kib_peer_t *peer, int why); void kiblnd_connreq_done(kib_conn_t *conn, int status); -kib_conn_t *kiblnd_create_conn (kib_peer_t *peer, struct rdma_cm_id *cmid, +kib_conn_t *kiblnd_create_conn(kib_peer_t *peer, struct rdma_cm_id *cmid, int state, int version); -void kiblnd_destroy_conn (kib_conn_t *conn); -void kiblnd_close_conn (kib_conn_t *conn, int error); -void kiblnd_close_conn_locked (kib_conn_t *conn, int error); +void kiblnd_destroy_conn(kib_conn_t *conn); +void kiblnd_close_conn(kib_conn_t *conn, int error); +void kiblnd_close_conn_locked(kib_conn_t *conn, int error); -int kiblnd_init_rdma (kib_conn_t *conn, kib_tx_t *tx, int type, +int kiblnd_init_rdma(kib_conn_t *conn, kib_tx_t *tx, int type, int nob, kib_rdma_desc_t *dstrd, __u64 dstcookie); -void kiblnd_launch_tx (lnet_ni_t *ni, kib_tx_t *tx, lnet_nid_t nid); -void kiblnd_queue_tx_locked (kib_tx_t *tx, kib_conn_t *conn); -void kiblnd_queue_tx (kib_tx_t *tx, kib_conn_t *conn); -void kiblnd_init_tx_msg (lnet_ni_t *ni, kib_tx_t *tx, int type, int body_nob); -void kiblnd_txlist_done (lnet_ni_t *ni, struct list_head *txlist, +void kiblnd_launch_tx(lnet_ni_t *ni, kib_tx_t *tx, lnet_nid_t nid); +void kiblnd_queue_tx_locked(kib_tx_t *tx, kib_conn_t *conn); +void kiblnd_queue_tx(kib_tx_t *tx, kib_conn_t *conn); +void kiblnd_init_tx_msg(lnet_ni_t *ni, kib_tx_t *tx, int type, int body_nob); +void kiblnd_txlist_done(lnet_ni_t *ni, struct list_head *txlist, int status); void kiblnd_check_sends (kib_conn_t *conn); @@ -1036,10 +1006,10 @@ void kiblnd_qp_event(struct ib_event *event, void *arg); void kiblnd_cq_event(struct ib_event *event, void *arg); void kiblnd_cq_completion(struct ib_cq *cq, void *arg); -void kiblnd_pack_msg (lnet_ni_t *ni, kib_msg_t *msg, int version, +void kiblnd_pack_msg(lnet_ni_t *ni, kib_msg_t *msg, int version, int credits, lnet_nid_t dstnid, __u64 dststamp); int kiblnd_unpack_msg(kib_msg_t *msg, int nob); -int kiblnd_post_rx (kib_rx_t *rx, int credit); +int kiblnd_post_rx(kib_rx_t *rx, int credit); int kiblnd_send(lnet_ni_t *ni, void *private, lnet_msg_t *lntmsg); int kiblnd_recv(lnet_ni_t *ni, void *private, lnet_msg_t *lntmsg, int delayed, diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c index 477aa8b76..a23a6d956 100644 --- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c +++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c @@ -121,7 +121,6 @@ kiblnd_get_idle_tx(lnet_ni_t *ni, lnet_nid_t target) LASSERT(tx->tx_conn == NULL); LASSERT(tx->tx_lntmsg[0] == NULL); LASSERT(tx->tx_lntmsg[1] == NULL); - LASSERT(tx->tx_u.pmr == NULL); LASSERT(tx->tx_nfrags == 0); return tx; @@ -575,7 +574,7 @@ kiblnd_fmr_map_tx(kib_net_t *net, kib_tx_t *tx, kib_rdma_desc_t *rd, int nob) cpt = tx->tx_pool->tpo_pool.po_owner->ps_cpt; fps = net->ibn_fmr_ps[cpt]; - rc = kiblnd_fmr_pool_map(fps, pages, npages, 0, &tx->tx_u.fmr); + rc = kiblnd_fmr_pool_map(fps, pages, npages, 0, &tx->fmr); if (rc != 0) { CERROR("Can't map %d pages: %d\n", npages, rc); return rc; @@ -583,8 +582,8 @@ kiblnd_fmr_map_tx(kib_net_t *net, kib_tx_t *tx, kib_rdma_desc_t *rd, int nob) /* If rd is not tx_rd, it's going to get sent to a peer, who will need * the rkey */ - rd->rd_key = (rd != tx->tx_rd) ? tx->tx_u.fmr.fmr_pfmr->fmr->rkey : - tx->tx_u.fmr.fmr_pfmr->fmr->lkey; + rd->rd_key = (rd != tx->tx_rd) ? tx->fmr.fmr_pfmr->fmr->rkey : + tx->fmr.fmr_pfmr->fmr->lkey; rd->rd_frags[0].rf_addr &= ~hdev->ibh_page_mask; rd->rd_frags[0].rf_nob = nob; rd->rd_nfrags = 1; @@ -592,42 +591,6 @@ kiblnd_fmr_map_tx(kib_net_t *net, kib_tx_t *tx, kib_rdma_desc_t *rd, int nob) return 0; } -static int -kiblnd_pmr_map_tx(kib_net_t *net, kib_tx_t *tx, kib_rdma_desc_t *rd, int nob) -{ - kib_hca_dev_t *hdev; - kib_pmr_poolset_t *pps; - __u64 iova; - int cpt; - int rc; - - LASSERT(tx->tx_pool != NULL); - LASSERT(tx->tx_pool->tpo_pool.po_owner != NULL); - - hdev = tx->tx_pool->tpo_hdev; - - iova = rd->rd_frags[0].rf_addr & ~hdev->ibh_page_mask; - - cpt = tx->tx_pool->tpo_pool.po_owner->ps_cpt; - - pps = net->ibn_pmr_ps[cpt]; - rc = kiblnd_pmr_pool_map(pps, hdev, rd, &iova, &tx->tx_u.pmr); - if (rc != 0) { - CERROR("Failed to create MR by phybuf: %d\n", rc); - return rc; - } - - /* If rd is not tx_rd, it's going to get sent to a peer, who will need - * the rkey */ - rd->rd_key = (rd != tx->tx_rd) ? tx->tx_u.pmr->pmr_mr->rkey : - tx->tx_u.pmr->pmr_mr->lkey; - rd->rd_nfrags = 1; - rd->rd_frags[0].rf_addr = iova; - rd->rd_frags[0].rf_nob = nob; - - return 0; -} - void kiblnd_unmap_tx(lnet_ni_t *ni, kib_tx_t *tx) { @@ -635,13 +598,9 @@ kiblnd_unmap_tx(lnet_ni_t *ni, kib_tx_t *tx) LASSERT(net != NULL); - if (net->ibn_fmr_ps != NULL && tx->tx_u.fmr.fmr_pfmr != NULL) { - kiblnd_fmr_pool_unmap(&tx->tx_u.fmr, tx->tx_status); - tx->tx_u.fmr.fmr_pfmr = NULL; - - } else if (net->ibn_pmr_ps != NULL && tx->tx_u.pmr != NULL) { - kiblnd_pmr_pool_unmap(tx->tx_u.pmr); - tx->tx_u.pmr = NULL; + if (net->ibn_fmr_ps && tx->fmr.fmr_pfmr) { + kiblnd_fmr_pool_unmap(&tx->fmr, tx->tx_status); + tx->fmr.fmr_pfmr = NULL; } if (tx->tx_nfrags != 0) { @@ -687,8 +646,6 @@ kiblnd_map_tx(lnet_ni_t *ni, kib_tx_t *tx, if (net->ibn_fmr_ps != NULL) return kiblnd_fmr_map_tx(net, tx, rd, nob); - else if (net->ibn_pmr_ps != NULL) - return kiblnd_pmr_map_tx(net, tx, rd, nob); return -EINVAL; } @@ -3133,8 +3090,7 @@ kiblnd_connd(void *arg) dropped_lock = 0; if (!list_empty(&kiblnd_data.kib_connd_zombies)) { - conn = list_entry(kiblnd_data. \ - kib_connd_zombies.next, + conn = list_entry(kiblnd_data.kib_connd_zombies.next, kib_conn_t, ibc_list); list_del(&conn->ibc_list); diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_modparams.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_modparams.c index b0e00361c..b3d1b5d62 100644 --- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_modparams.c +++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_modparams.c @@ -126,11 +126,6 @@ static int fmr_cache = 1; module_param(fmr_cache, int, 0444); MODULE_PARM_DESC(fmr_cache, "non-zero to enable FMR caching"); -/* NB: this value is shared by all CPTs, it can grow at runtime */ -static int pmr_pool_size = 512; -module_param(pmr_pool_size, int, 0444); -MODULE_PARM_DESC(pmr_pool_size, "size of MR cache pmr pool on each CPT"); - /* * 0: disable failover * 1: enable failover if necessary @@ -170,7 +165,6 @@ kib_tunables_t kiblnd_tunables = { .kib_fmr_pool_size = &fmr_pool_size, .kib_fmr_flush_trigger = &fmr_flush_trigger, .kib_fmr_cache = &fmr_cache, - .kib_pmr_pool_size = &pmr_pool_size, .kib_require_priv_port = &require_privileged_port, .kib_use_priv_port = &use_privileged_port, .kib_nscheds = &nscheds -- cgit v1.2.3-54-g00ecf