From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/net/rds/ib_rdma.c | 169 ++++++++++++++++++++++++++++++++++++--------------------
1 files changed, 109 insertions(+), 60 deletions(-)
diff --git a/kernel/net/rds/ib_rdma.c b/kernel/net/rds/ib_rdma.c
index f395f06..8f070ee 100644
--- a/kernel/net/rds/ib_rdma.c
+++ b/kernel/net/rds/ib_rdma.c
@@ -34,15 +34,18 @@
#include <linux/slab.h>
#include <linux/rculist.h>
#include <linux/llist.h>
-#include <linux/delay.h>
#include "rds_single_path.h"
#include "ib_mr.h"
+#include "rds.h"
struct workqueue_struct *rds_ib_mr_wq;
+struct rds_ib_dereg_odp_mr {
+ struct work_struct work;
+ struct ib_mr *mr;
+};
-static DEFINE_PER_CPU(unsigned long, clean_list_grace);
-#define CLEAN_LIST_BUSY_BIT 0
+static void rds_ib_odp_mr_worker(struct work_struct *work);
static struct rds_ib_device *rds_ib_get_device(__be32 ipaddr)
{
@@ -178,7 +181,7 @@
struct rds_ib_mr_pool *pool_1m = rds_ibdev->mr_1m_pool;
iinfo->rdma_mr_max = pool_1m->max_items;
- iinfo->rdma_mr_size = pool_1m->fmr_attr.max_pages;
+ iinfo->rdma_mr_size = pool_1m->max_pages;
}
#if IS_ENABLED(CONFIG_IPV6)
@@ -188,7 +191,7 @@
struct rds_ib_mr_pool *pool_1m = rds_ibdev->mr_1m_pool;
iinfo6->rdma_mr_max = pool_1m->max_items;
- iinfo6->rdma_mr_size = pool_1m->fmr_attr.max_pages;
+ iinfo6->rdma_mr_size = pool_1m->max_pages;
}
#endif
@@ -196,12 +199,11 @@
{
struct rds_ib_mr *ibmr = NULL;
struct llist_node *ret;
- unsigned long *flag;
+ unsigned long flags;
- preempt_disable();
- flag = this_cpu_ptr(&clean_list_grace);
- set_bit(CLEAN_LIST_BUSY_BIT, flag);
+ spin_lock_irqsave(&pool->clean_lock, flags);
ret = llist_del_first(&pool->clean_list);
+ spin_unlock_irqrestore(&pool->clean_lock, flags);
if (ret) {
ibmr = llist_entry(ret, struct rds_ib_mr, llnode);
if (pool->pool_type == RDS_IB_MR_8K_POOL)
@@ -210,27 +212,16 @@
rds_ib_stats_inc(s_ib_rdma_mr_1m_reused);
}
- clear_bit(CLEAN_LIST_BUSY_BIT, flag);
- preempt_enable();
return ibmr;
-}
-
-static inline void wait_clean_list_grace(void)
-{
- int cpu;
- unsigned long *flag;
-
- for_each_online_cpu(cpu) {
- flag = &per_cpu(clean_list_grace, cpu);
- while (test_bit(CLEAN_LIST_BUSY_BIT, flag))
- cpu_chill();
- }
}
void rds_ib_sync_mr(void *trans_private, int direction)
{
struct rds_ib_mr *ibmr = trans_private;
struct rds_ib_device *rds_ibdev = ibmr->device;
+
+ if (ibmr->odp)
+ return;
switch (direction) {
case DMA_FROM_DEVICE:
@@ -325,8 +316,7 @@
* of clusters. Each cluster has linked llist nodes of
* MR_CLUSTER_SIZE mrs that are ready for reuse.
*/
-static void list_to_llist_nodes(struct rds_ib_mr_pool *pool,
- struct list_head *list,
+static void list_to_llist_nodes(struct list_head *list,
struct llist_node **nodes_head,
struct llist_node **nodes_tail)
{
@@ -403,41 +393,36 @@
*/
dirty_to_clean = llist_append_to_list(&pool->drop_list, &unmap_list);
dirty_to_clean += llist_append_to_list(&pool->free_list, &unmap_list);
- if (free_all)
+ if (free_all) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&pool->clean_lock, flags);
llist_append_to_list(&pool->clean_list, &unmap_list);
+ spin_unlock_irqrestore(&pool->clean_lock, flags);
+ }
free_goal = rds_ib_flush_goal(pool, free_all);
if (list_empty(&unmap_list))
goto out;
- if (pool->use_fastreg)
- rds_ib_unreg_frmr(&unmap_list, &nfreed, &unpinned, free_goal);
- else
- rds_ib_unreg_fmr(&unmap_list, &nfreed, &unpinned, free_goal);
+ rds_ib_unreg_frmr(&unmap_list, &nfreed, &unpinned, free_goal);
if (!list_empty(&unmap_list)) {
- /* we have to make sure that none of the things we're about
- * to put on the clean list would race with other cpus trying
- * to pull items off. The llist would explode if we managed to
- * remove something from the clean list and then add it back again
- * while another CPU was spinning on that same item in llist_del_first.
- *
- * This is pretty unlikely, but just in case wait for an llist grace period
- * here before adding anything back into the clean list.
- */
- wait_clean_list_grace();
+ unsigned long flags;
- list_to_llist_nodes(pool, &unmap_list, &clean_nodes, &clean_tail);
+ list_to_llist_nodes(&unmap_list, &clean_nodes, &clean_tail);
if (ibmr_ret) {
*ibmr_ret = llist_entry(clean_nodes, struct rds_ib_mr, llnode);
clean_nodes = clean_nodes->next;
}
/* more than one entry in llist nodes */
- if (clean_nodes)
+ if (clean_nodes) {
+ spin_lock_irqsave(&pool->clean_lock, flags);
llist_add_batch(clean_nodes, clean_tail,
&pool->clean_list);
-
+ spin_unlock_irqrestore(&pool->clean_lock, flags);
+ }
}
atomic_sub(unpinned, &pool->free_pinned);
@@ -472,7 +457,7 @@
rds_ib_stats_inc(s_ib_rdma_mr_8k_pool_depleted);
else
rds_ib_stats_inc(s_ib_rdma_mr_1m_pool_depleted);
- return ERR_PTR(-EAGAIN);
+ break;
}
/* We do have some empty MRs. Flush them out. */
@@ -486,7 +471,7 @@
return ibmr;
}
- return ibmr;
+ return NULL;
}
static void rds_ib_mr_pool_flush_worker(struct work_struct *work)
@@ -504,11 +489,18 @@
rdsdebug("RDS/IB: free_mr nents %u\n", ibmr->sg_len);
+ if (ibmr->odp) {
+ /* A MR created and marked as use_once. We use delayed work,
+ * because there is a change that we are in interrupt and can't
+ * call to ib_dereg_mr() directly.
+ */
+ INIT_DELAYED_WORK(&ibmr->work, rds_ib_odp_mr_worker);
+ queue_delayed_work(rds_ib_mr_wq, &ibmr->work, 0);
+ return;
+ }
+
/* Return it to the pool's free list */
- if (rds_ibdev->use_fastreg)
- rds_ib_free_frmr_list(ibmr);
- else
- rds_ib_free_fmr_list(ibmr);
+ rds_ib_free_frmr_list(ibmr);
atomic_add(ibmr->sg_len, &pool->free_pinned);
atomic_inc(&pool->dirty_count);
@@ -548,9 +540,17 @@
up_read(&rds_ib_devices_lock);
}
+u32 rds_ib_get_lkey(void *trans_private)
+{
+ struct rds_ib_mr *ibmr = trans_private;
+
+ return ibmr->u.mr->lkey;
+}
+
void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
struct rds_sock *rs, u32 *key_ret,
- struct rds_connection *conn)
+ struct rds_connection *conn,
+ u64 start, u64 length, int need_odp)
{
struct rds_ib_device *rds_ibdev;
struct rds_ib_mr *ibmr = NULL;
@@ -563,6 +563,51 @@
goto out;
}
+ if (need_odp == ODP_ZEROBASED || need_odp == ODP_VIRTUAL) {
+ u64 virt_addr = need_odp == ODP_ZEROBASED ? 0 : start;
+ int access_flags =
+ (IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_READ |
+ IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_ATOMIC |
+ IB_ACCESS_ON_DEMAND);
+ struct ib_sge sge = {};
+ struct ib_mr *ib_mr;
+
+ if (!rds_ibdev->odp_capable) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+
+ ib_mr = ib_reg_user_mr(rds_ibdev->pd, start, length, virt_addr,
+ access_flags);
+
+ if (IS_ERR(ib_mr)) {
+ rdsdebug("rds_ib_get_user_mr returned %d\n",
+ IS_ERR(ib_mr));
+ ret = PTR_ERR(ib_mr);
+ goto out;
+ }
+ if (key_ret)
+ *key_ret = ib_mr->rkey;
+
+ ibmr = kzalloc(sizeof(*ibmr), GFP_KERNEL);
+ if (!ibmr) {
+ ib_dereg_mr(ib_mr);
+ ret = -ENOMEM;
+ goto out;
+ }
+ ibmr->u.mr = ib_mr;
+ ibmr->odp = 1;
+
+ sge.addr = virt_addr;
+ sge.length = length;
+ sge.lkey = ib_mr->lkey;
+
+ ib_advise_mr(rds_ibdev->pd,
+ IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE,
+ IB_UVERBS_ADVISE_MR_FLAG_FLUSH, &sge, 1);
+ return ibmr;
+ }
+
if (conn)
ic = conn->c_transport_data;
@@ -571,10 +616,7 @@
goto out;
}
- if (rds_ibdev->use_fastreg)
- ibmr = rds_ib_reg_frmr(rds_ibdev, ic, sg, nents, key_ret);
- else
- ibmr = rds_ib_reg_fmr(rds_ibdev, sg, nents, key_ret);
+ ibmr = rds_ib_reg_frmr(rds_ibdev, ic, sg, nents, key_ret);
if (IS_ERR(ibmr)) {
ret = PTR_ERR(ibmr);
pr_warn("RDS/IB: rds_ib_get_mr failed (errno=%d)\n", ret);
@@ -611,25 +653,23 @@
init_llist_head(&pool->free_list);
init_llist_head(&pool->drop_list);
init_llist_head(&pool->clean_list);
+ spin_lock_init(&pool->clean_lock);
mutex_init(&pool->flush_lock);
init_waitqueue_head(&pool->flush_wait);
INIT_DELAYED_WORK(&pool->flush_worker, rds_ib_mr_pool_flush_worker);
if (pool_type == RDS_IB_MR_1M_POOL) {
/* +1 allows for unaligned MRs */
- pool->fmr_attr.max_pages = RDS_MR_1M_MSG_SIZE + 1;
+ pool->max_pages = RDS_MR_1M_MSG_SIZE + 1;
pool->max_items = rds_ibdev->max_1m_mrs;
} else {
/* pool_type == RDS_IB_MR_8K_POOL */
- pool->fmr_attr.max_pages = RDS_MR_8K_MSG_SIZE + 1;
+ pool->max_pages = RDS_MR_8K_MSG_SIZE + 1;
pool->max_items = rds_ibdev->max_8k_mrs;
}
- pool->max_free_pinned = pool->max_items * pool->fmr_attr.max_pages / 4;
- pool->fmr_attr.max_maps = rds_ibdev->fmr_max_remaps;
- pool->fmr_attr.page_shift = PAGE_SHIFT;
+ pool->max_free_pinned = pool->max_items * pool->max_pages / 4;
pool->max_items_soft = rds_ibdev->max_mrs * 3 / 4;
- pool->use_fastreg = rds_ibdev->use_fastreg;
return pool;
}
@@ -650,3 +690,12 @@
{
destroy_workqueue(rds_ib_mr_wq);
}
+
+static void rds_ib_odp_mr_worker(struct work_struct *work)
+{
+ struct rds_ib_mr *ibmr;
+
+ ibmr = container_of(work, struct rds_ib_mr, work.work);
+ ib_dereg_mr(ibmr->u.mr);
+ kfree(ibmr);
+}
--
Gitblit v1.6.2