[lustre-devel] [PATCH 007/151] lnet: Allocate MEs and small MDs in own kmem_caches
James Simmons
jsimmons at infradead.org
Mon Sep 30 11:54:26 PDT 2019
From: Bruno Faccini <bruno.faccini at intel.com>
As part of LU-3848 and LU-4330, it has been discovered that LNET
MEs and small MDs (<=128 Bytes) are allocated in <size-128> kmem_cache
and thus can suffer quite frequent corruptions, from other modules or
Kernel parts, that occur there. To avoid this, MEs and small-MDs
specific kmem_cache have been created.
Also, lnet_libmd struct fields have been re-ordered to optimize its
memory foot-print.
WC-bug-id: https://jira.whamcloud.com/browse/LU-4330
Lustre-commit: 9d9bb678d6b3 ("LU-4330 lnet: Allocate MEs and small MDs in own kmem_caches")
Signed-off-by: Bruno Faccini <bruno.faccini at intel.com>
Reviewed-on: http://review.whamcloud.com/18586
Reviewed-by: Andreas Dilger <adilger at whamcloud.com>
Reviewed-by: Doug Oucharek <dougso at me.com>
Reviewed-by: Oleg Drokin <green at whamcloud.com>
Signed-off-by: James Simmons <jsimmons at infradead.org>
---
include/linux/lnet/lib-lnet.h | 39 ++++++++++++++++++++++++++++++++++++++-
include/linux/lnet/lib-types.h | 2 +-
net/lnet/lnet/api-ni.c | 40 ++++++++++++++++++++++++++++++++++++++++
net/lnet/lnet/lib-md.c | 2 +-
net/lnet/lnet/lib-me.c | 2 +-
net/lnet/lnet/lib-ptl.c | 2 +-
6 files changed, 82 insertions(+), 5 deletions(-)
diff --git a/include/linux/lnet/lib-lnet.h b/include/linux/lnet/lib-lnet.h
index 776896a..538d457 100644
--- a/include/linux/lnet/lib-lnet.h
+++ b/include/linux/lnet/lib-lnet.h
@@ -80,6 +80,12 @@
/* default timeout */
#define DEFAULT_PEER_TIMEOUT 180
+#define LNET_SMALL_MD_SIZE offsetof(struct lnet_libmd, md_iov.iov[1])
+extern struct kmem_cache *lnet_mes_cachep; /* MEs kmem_cache */
+extern struct kmem_cache *lnet_small_mds_cachep; /* <= LNET_SMALL_MD_SIZE bytes
+ * MDs kmem_cache
+ */
+
static inline int lnet_is_route_alive(struct lnet_route *route)
{
/* gateway is down */
@@ -151,6 +157,24 @@ static inline int lnet_md_unlinkable(struct lnet_libmd *md)
cfs_percpt_unlock(the_lnet.ln_res_lock, cpt);
}
+static inline void
+lnet_md_free(struct lnet_libmd *md)
+{
+ unsigned int size;
+
+ if ((md->md_options & LNET_MD_KIOV) != 0)
+ size = offsetof(struct lnet_libmd, md_iov.kiov[md->md_niov]);
+ else
+ size = offsetof(struct lnet_libmd, md_iov.iov[md->md_niov]);
+
+ if (size <= LNET_SMALL_MD_SIZE) {
+ CDEBUG(D_MALLOC, "slab-freed 'md' at %p.\n", md);
+ kmem_cache_free(lnet_small_mds_cachep, md);
+ } else {
+ kfree(md);
+ }
+}
+
static inline int
lnet_res_lock_current(void)
{
@@ -205,7 +229,20 @@ static inline int lnet_md_unlinkable(struct lnet_libmd *md)
size = offsetof(struct lnet_libmd, md_iov.iov[niov]);
}
- md = kzalloc(size, GFP_NOFS);
+ if (size <= LNET_SMALL_MD_SIZE) {
+ md = kmem_cache_alloc(lnet_small_mds_cachep,
+ GFP_NOFS | __GFP_ZERO);
+ if (md) {
+ CDEBUG(D_MALLOC,
+ "slab-alloced 'md' of size %u at %p.\n",
+ size, md);
+ } else {
+ CDEBUG(D_MALLOC, "failed to allocate 'md' of size %u\n",
+ size);
+ }
+ } else {
+ md = kzalloc(size, GFP_NOFS);
+ }
if (md) {
/* Set here in case of early free */
md->md_options = umd->options;
diff --git a/include/linux/lnet/lib-types.h b/include/linux/lnet/lib-types.h
index 60f9c28..6d2d83a 100644
--- a/include/linux/lnet/lib-types.h
+++ b/include/linux/lnet/lib-types.h
@@ -164,9 +164,9 @@ struct lnet_libmd {
int md_refcount;
unsigned int md_options;
unsigned int md_flags;
+ unsigned int md_niov; /* # frags at end of struct */
void *md_user_ptr;
struct lnet_eq *md_eq;
- unsigned int md_niov; /* # frags */
struct lnet_handle_md md_bulk_handle;
union {
struct kvec iov[LNET_MAX_IOV];
diff --git a/net/lnet/lnet/api-ni.c b/net/lnet/lnet/api-ni.c
index 12b3c44..c33cd1f 100644
--- a/net/lnet/lnet/api-ni.c
+++ b/net/lnet/lnet/api-ni.c
@@ -216,6 +216,41 @@ static int lnet_discover(struct lnet_process_id id, u32 force,
mutex_init(&the_lnet.ln_lnd_mutex);
}
+struct kmem_cache *lnet_mes_cachep; /* MEs kmem_cache */
+struct kmem_cache *lnet_small_mds_cachep; /* <= LNET_SMALL_MD_SIZE bytes
+ * MDs kmem_cache
+ */
+
+static int
+lnet_descriptor_setup(void)
+{
+ /* create specific kmem_cache for MEs and small MDs (i.e., originally
+ * allocated in <size-xxx> kmem_cache).
+ */
+ lnet_mes_cachep = kmem_cache_create("lnet_MEs", sizeof(struct lnet_me),
+ 0, 0, NULL);
+ if (!lnet_mes_cachep)
+ return -ENOMEM;
+
+ lnet_small_mds_cachep = kmem_cache_create("lnet_small_MDs",
+ LNET_SMALL_MD_SIZE, 0, 0,
+ NULL);
+ if (!lnet_small_mds_cachep)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void
+lnet_descriptor_cleanup(void)
+{
+ kmem_cache_destroy(lnet_small_mds_cachep);
+ lnet_small_mds_cachep = NULL;
+
+ kmem_cache_destroy(lnet_mes_cachep);
+ lnet_mes_cachep = NULL;
+}
+
static int
lnet_create_remote_nets_table(void)
{
@@ -701,6 +736,10 @@ struct lnet_libhandle *
INIT_LIST_HEAD(&the_lnet.ln_dc_expired);
init_waitqueue_head(&the_lnet.ln_dc_waitq);
+ rc = lnet_descriptor_setup();
+ if (rc != 0)
+ goto failed;
+
rc = lnet_create_remote_nets_table();
if (rc)
goto failed;
@@ -798,6 +837,7 @@ struct lnet_libhandle *
the_lnet.ln_counters = NULL;
}
lnet_destroy_remote_nets_table();
+ lnet_descriptor_cleanup();
return 0;
}
diff --git a/net/lnet/lnet/lib-md.c b/net/lnet/lnet/lib-md.c
index 33a59fb..8fe3564 100644
--- a/net/lnet/lnet/lib-md.c
+++ b/net/lnet/lnet/lib-md.c
@@ -82,7 +82,7 @@
LASSERT(!list_empty(&md->md_list));
list_del_init(&md->md_list);
- kfree(md);
+ lnet_md_free(md);
}
struct page *lnet_kvaddr_to_page(unsigned long vaddr)
diff --git a/net/lnet/lnet/lib-me.c b/net/lnet/lnet/lib-me.c
index f0365ea..4fe6991 100644
--- a/net/lnet/lnet/lib-me.c
+++ b/net/lnet/lnet/lib-me.c
@@ -91,7 +91,7 @@
if (!mtable) /* can't match portal type */
return -EPERM;
- me = kzalloc(sizeof(*me), GFP_NOFS);
+ me = kmem_cache_alloc(lnet_mes_cachep, GFP_NOFS | __GFP_ZERO);
if (!me)
return -ENOMEM;
diff --git a/net/lnet/lnet/lib-ptl.c b/net/lnet/lnet/lib-ptl.c
index ae061e8..83548f5 100644
--- a/net/lnet/lnet/lib-ptl.c
+++ b/net/lnet/lnet/lib-ptl.c
@@ -773,7 +773,7 @@ struct list_head *
!= NULL) {
CERROR("Active ME %p on exit\n", me);
list_del(&me->me_list);
- kfree(me);
+ kmem_cache_free(lnet_mes_cachep, me);
}
}
/* the extra entry is for MEs with ignore bits */
--
1.8.3.1
More information about the lustre-devel
mailing list