* [PATCH v8 08/16] block, elevator: use new hashtable implementation
From: Sasha Levin @ 2012-10-30 18:46 UTC (permalink / raw)
To: torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b
Cc: snitzer-H+wXaHxf7aLQT0dZR+AlfA, neilb-l3A5Bk7waGM,
fweisbec-Re5JQEeQqe8AvxtiuMwx3w,
Trond.Myklebust-HgOvQuBEEgTQT0dZR+AlfA,
bfields-uC3wQj2KruNg9hUCZPvPmw,
paul.gortmaker-CWA4WttNNZF54TAoqtyWWQ,
dm-devel-H+wXaHxf7aLQT0dZR+AlfA, agk-H+wXaHxf7aLQT0dZR+AlfA,
aarcange-H+wXaHxf7aLQT0dZR+AlfA, rds-devel-N0ozoZBvEnrZJqsBc5GL+g,
eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w,
venkat.x.venkatsubra-QHcLZuEGTsvQT0dZR+AlfA,
ccaulfie-H+wXaHxf7aLQT0dZR+AlfA, mingo-X9Un+BFzKDI,
dev-yBygre7rU0TnMu66kgdUjQ, ericvh-Re5JQEeQqe8AvxtiuMwx3w,
josh-iaAMLnmF4UmaiuxdJuQwMA, rostedt-nx8X9YLhiw1AfugRpC6u6w,
lw-BthXqXjhjHXQFUHtdCDX3A,
mathieu.desnoyers-vg+e7yoeK/dWk0Htik3J/w, Sasha Levin,
axboe-tSWWG44O7X1aa/9Udqfwiw, linux-nfs-u79uwXL29TY76Z2rM5mHXA,
edumazet-hpIqsD4AKlfQT0dZR+AlfA, linux-mm-Bw31MaZKKs3YtjvyW6yDsg,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, ejt-H+wXaHxf7aLQT0dZR+AlfA,
ebiederm-aS9lmoZGLiVWk0Htik3J/w, tj-DgEjT+Ai2ygdnm+yROfE0A,
teigland-H+wXaHxf7aLQT0dZR+AlfA,
akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
In-Reply-To: <1351622772-16400-1-git-send-email-levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Switch elevator to use the new hashtable implementation. This reduces the
amount of generic unrelated code in the elevator.
This also removes the dymanic allocation of the hash table. The size of the table is
constant so there's no point in paying the price of an extra dereference when accessing
it.
Signed-off-by: Sasha Levin <levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---
block/blk.h | 2 +-
block/elevator.c | 23 ++++-------------------
include/linux/elevator.h | 5 ++++-
3 files changed, 9 insertions(+), 21 deletions(-)
diff --git a/block/blk.h b/block/blk.h
index ca51543..a0abbf6 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -61,7 +61,7 @@ static inline void blk_clear_rq_complete(struct request *rq)
/*
* Internal elevator interface
*/
-#define ELV_ON_HASH(rq) (!hlist_unhashed(&(rq)->hash))
+#define ELV_ON_HASH(rq) hash_hashed(&(rq)->hash)
void blk_insert_flush(struct request *rq);
void blk_abort_flushes(struct request_queue *q);
diff --git a/block/elevator.c b/block/elevator.c
index 9b1d42b..898d0eb 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -46,11 +46,6 @@ static LIST_HEAD(elv_list);
/*
* Merge hash stuff.
*/
-static const int elv_hash_shift = 6;
-#define ELV_HASH_BLOCK(sec) ((sec) >> 3)
-#define ELV_HASH_FN(sec) \
- (hash_long(ELV_HASH_BLOCK((sec)), elv_hash_shift))
-#define ELV_HASH_ENTRIES (1 << elv_hash_shift)
#define rq_hash_key(rq) (blk_rq_pos(rq) + blk_rq_sectors(rq))
/*
@@ -142,7 +137,6 @@ static struct elevator_queue *elevator_alloc(struct request_queue *q,
struct elevator_type *e)
{
struct elevator_queue *eq;
- int i;
eq = kmalloc_node(sizeof(*eq), GFP_KERNEL | __GFP_ZERO, q->node);
if (unlikely(!eq))
@@ -151,14 +145,7 @@ static struct elevator_queue *elevator_alloc(struct request_queue *q,
eq->type = e;
kobject_init(&eq->kobj, &elv_ktype);
mutex_init(&eq->sysfs_lock);
-
- eq->hash = kmalloc_node(sizeof(struct hlist_head) * ELV_HASH_ENTRIES,
- GFP_KERNEL, q->node);
- if (!eq->hash)
- goto err;
-
- for (i = 0; i < ELV_HASH_ENTRIES; i++)
- INIT_HLIST_HEAD(&eq->hash[i]);
+ hash_init(eq->hash);
return eq;
err:
@@ -173,7 +160,6 @@ static void elevator_release(struct kobject *kobj)
e = container_of(kobj, struct elevator_queue, kobj);
elevator_put(e->type);
- kfree(e->hash);
kfree(e);
}
@@ -240,7 +226,7 @@ EXPORT_SYMBOL(elevator_exit);
static inline void __elv_rqhash_del(struct request *rq)
{
- hlist_del_init(&rq->hash);
+ hash_del(&rq->hash);
}
static void elv_rqhash_del(struct request_queue *q, struct request *rq)
@@ -254,7 +240,7 @@ static void elv_rqhash_add(struct request_queue *q, struct request *rq)
struct elevator_queue *e = q->elevator;
BUG_ON(ELV_ON_HASH(rq));
- hlist_add_head(&rq->hash, &e->hash[ELV_HASH_FN(rq_hash_key(rq))]);
+ hash_add(e->hash, &rq->hash, rq_hash_key(rq));
}
static void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
@@ -266,11 +252,10 @@ static void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
static struct request *elv_rqhash_find(struct request_queue *q, sector_t offset)
{
struct elevator_queue *e = q->elevator;
- struct hlist_head *hash_list = &e->hash[ELV_HASH_FN(offset)];
struct hlist_node *entry, *next;
struct request *rq;
- hlist_for_each_entry_safe(rq, entry, next, hash_list, hash) {
+ hash_for_each_possible_safe(e->hash, rq, entry, next, hash, offset) {
BUG_ON(!ELV_ON_HASH(rq));
if (unlikely(!rq_mergeable(rq))) {
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index c03af76..7c5a7c9 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -2,6 +2,7 @@
#define _LINUX_ELEVATOR_H
#include <linux/percpu.h>
+#include <linux/hashtable.h>
#ifdef CONFIG_BLOCK
@@ -96,6 +97,8 @@ struct elevator_type
struct list_head list;
};
+#define ELV_HASH_BITS 6
+
/*
* each queue has an elevator_queue associated with it
*/
@@ -105,8 +108,8 @@ struct elevator_queue
void *elevator_data;
struct kobject kobj;
struct mutex sysfs_lock;
- struct hlist_head *hash;
unsigned int registered:1;
+ DECLARE_HASHTABLE(hash, ELV_HASH_BITS);
};
/*
--
1.7.12.4
^ permalink raw reply related
* [PATCH v8 07/16] net, 9p: use new hashtable implementation
From: Sasha Levin @ 2012-10-30 18:46 UTC (permalink / raw)
To: torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b
Cc: snitzer-H+wXaHxf7aLQT0dZR+AlfA, neilb-l3A5Bk7waGM,
fweisbec-Re5JQEeQqe8AvxtiuMwx3w,
Trond.Myklebust-HgOvQuBEEgTQT0dZR+AlfA,
bfields-uC3wQj2KruNg9hUCZPvPmw,
paul.gortmaker-CWA4WttNNZF54TAoqtyWWQ,
dm-devel-H+wXaHxf7aLQT0dZR+AlfA, agk-H+wXaHxf7aLQT0dZR+AlfA,
aarcange-H+wXaHxf7aLQT0dZR+AlfA, rds-devel-N0ozoZBvEnrZJqsBc5GL+g,
eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w,
venkat.x.venkatsubra-QHcLZuEGTsvQT0dZR+AlfA,
ccaulfie-H+wXaHxf7aLQT0dZR+AlfA, mingo-X9Un+BFzKDI,
dev-yBygre7rU0TnMu66kgdUjQ, ericvh-Re5JQEeQqe8AvxtiuMwx3w,
josh-iaAMLnmF4UmaiuxdJuQwMA, rostedt-nx8X9YLhiw1AfugRpC6u6w,
lw-BthXqXjhjHXQFUHtdCDX3A,
mathieu.desnoyers-vg+e7yoeK/dWk0Htik3J/w, Sasha Levin,
axboe-tSWWG44O7X1aa/9Udqfwiw, linux-nfs-u79uwXL29TY76Z2rM5mHXA,
edumazet-hpIqsD4AKlfQT0dZR+AlfA, linux-mm-Bw31MaZKKs3YtjvyW6yDsg,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, ejt-H+wXaHxf7aLQT0dZR+AlfA,
ebiederm-aS9lmoZGLiVWk0Htik3J/w, tj-DgEjT+Ai2ygdnm+yROfE0A,
teigland-H+wXaHxf7aLQT0dZR+AlfA,
akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
In-Reply-To: <1351622772-16400-1-git-send-email-levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Switch 9p error table to use the new hashtable implementation. This reduces
the amount of generic unrelated code in 9p.
Signed-off-by: Sasha Levin <levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---
net/9p/error.c | 21 +++++++++------------
1 file changed, 9 insertions(+), 12 deletions(-)
diff --git a/net/9p/error.c b/net/9p/error.c
index 2ab2de7..a394b37 100644
--- a/net/9p/error.c
+++ b/net/9p/error.c
@@ -34,6 +34,7 @@
#include <linux/jhash.h>
#include <linux/errno.h>
#include <net/9p/9p.h>
+#include <linux/hashtable.h>
/**
* struct errormap - map string errors from Plan 9 to Linux numeric ids
@@ -50,8 +51,8 @@ struct errormap {
struct hlist_node list;
};
-#define ERRHASHSZ 32
-static struct hlist_head hash_errmap[ERRHASHSZ];
+#define ERR_HASH_BITS 5
+static DEFINE_HASHTABLE(hash_errmap, ERR_HASH_BITS);
/* FixMe - reduce to a reasonable size */
static struct errormap errmap[] = {
@@ -193,18 +194,14 @@ static struct errormap errmap[] = {
int p9_error_init(void)
{
struct errormap *c;
- int bucket;
-
- /* initialize hash table */
- for (bucket = 0; bucket < ERRHASHSZ; bucket++)
- INIT_HLIST_HEAD(&hash_errmap[bucket]);
+ u32 hash;
/* load initial error map into hash table */
for (c = errmap; c->name != NULL; c++) {
c->namelen = strlen(c->name);
- bucket = jhash(c->name, c->namelen, 0) % ERRHASHSZ;
+ hash = jhash(c->name, c->namelen, 0);
INIT_HLIST_NODE(&c->list);
- hlist_add_head(&c->list, &hash_errmap[bucket]);
+ hash_add(hash_errmap, &c->list, hash);
}
return 1;
@@ -223,13 +220,13 @@ int p9_errstr2errno(char *errstr, int len)
int errno;
struct hlist_node *p;
struct errormap *c;
- int bucket;
+ u32 hash;
errno = 0;
p = NULL;
c = NULL;
- bucket = jhash(errstr, len, 0) % ERRHASHSZ;
- hlist_for_each_entry(c, p, &hash_errmap[bucket], list) {
+ hash = jhash(errstr, len, 0);
+ hash_for_each_possible(hash_errmap, c, p, list, hash) {
if (c->namelen == len && !memcmp(c->name, errstr, len)) {
errno = c->val;
break;
--
1.7.12.4
^ permalink raw reply related
* [PATCH v8 06/16] tracepoint: use new hashtable implementation
From: Sasha Levin @ 2012-10-30 18:46 UTC (permalink / raw)
To: torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b
Cc: snitzer-H+wXaHxf7aLQT0dZR+AlfA, neilb-l3A5Bk7waGM,
fweisbec-Re5JQEeQqe8AvxtiuMwx3w,
Trond.Myklebust-HgOvQuBEEgTQT0dZR+AlfA,
bfields-uC3wQj2KruNg9hUCZPvPmw,
paul.gortmaker-CWA4WttNNZF54TAoqtyWWQ,
dm-devel-H+wXaHxf7aLQT0dZR+AlfA, agk-H+wXaHxf7aLQT0dZR+AlfA,
aarcange-H+wXaHxf7aLQT0dZR+AlfA, rds-devel-N0ozoZBvEnrZJqsBc5GL+g,
eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w,
venkat.x.venkatsubra-QHcLZuEGTsvQT0dZR+AlfA,
ccaulfie-H+wXaHxf7aLQT0dZR+AlfA, mingo-X9Un+BFzKDI,
dev-yBygre7rU0TnMu66kgdUjQ, ericvh-Re5JQEeQqe8AvxtiuMwx3w,
josh-iaAMLnmF4UmaiuxdJuQwMA, rostedt-nx8X9YLhiw1AfugRpC6u6w,
lw-BthXqXjhjHXQFUHtdCDX3A,
mathieu.desnoyers-vg+e7yoeK/dWk0Htik3J/w, Sasha Levin,
axboe-tSWWG44O7X1aa/9Udqfwiw, linux-nfs-u79uwXL29TY76Z2rM5mHXA,
edumazet-hpIqsD4AKlfQT0dZR+AlfA, linux-mm-Bw31MaZKKs3YtjvyW6yDsg,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, ejt-H+wXaHxf7aLQT0dZR+AlfA,
ebiederm-aS9lmoZGLiVWk0Htik3J/w, tj-DgEjT+Ai2ygdnm+yROfE0A,
teigland-H+wXaHxf7aLQT0dZR+AlfA,
akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
In-Reply-To: <1351622772-16400-1-git-send-email-levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Switch tracepoints to use the new hashtable implementation. This reduces the
amount of generic unrelated code in the tracepoints.
Signed-off-by: Sasha Levin <levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---
kernel/tracepoint.c | 25 +++++++++----------------
1 file changed, 9 insertions(+), 16 deletions(-)
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index d96ba22..5b599f1 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -26,6 +26,7 @@
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/static_key.h>
+#include <linux/hashtable.h>
extern struct tracepoint * const __start___tracepoints_ptrs[];
extern struct tracepoint * const __stop___tracepoints_ptrs[];
@@ -49,8 +50,7 @@ static LIST_HEAD(tracepoint_module_list);
* Protected by tracepoints_mutex.
*/
#define TRACEPOINT_HASH_BITS 6
-#define TRACEPOINT_TABLE_SIZE (1 << TRACEPOINT_HASH_BITS)
-static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE];
+static DEFINE_HASHTABLE(tracepoint_table, TRACEPOINT_HASH_BITS);
/*
* Note about RCU :
@@ -191,16 +191,15 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry,
*/
static struct tracepoint_entry *get_tracepoint(const char *name)
{
- struct hlist_head *head;
struct hlist_node *node;
struct tracepoint_entry *e;
u32 hash = jhash(name, strlen(name), 0);
- head = &tracepoint_table[hash & (TRACEPOINT_TABLE_SIZE - 1)];
- hlist_for_each_entry(e, node, head, hlist) {
+ hash_for_each_possible(tracepoint_table, e, node, hlist, hash) {
if (!strcmp(name, e->name))
return e;
}
+
return NULL;
}
@@ -210,19 +209,13 @@ static struct tracepoint_entry *get_tracepoint(const char *name)
*/
static struct tracepoint_entry *add_tracepoint(const char *name)
{
- struct hlist_head *head;
- struct hlist_node *node;
struct tracepoint_entry *e;
size_t name_len = strlen(name) + 1;
u32 hash = jhash(name, name_len-1, 0);
- head = &tracepoint_table[hash & (TRACEPOINT_TABLE_SIZE - 1)];
- hlist_for_each_entry(e, node, head, hlist) {
- if (!strcmp(name, e->name)) {
- printk(KERN_NOTICE
- "tracepoint %s busy\n", name);
- return ERR_PTR(-EEXIST); /* Already there */
- }
+ if (get_tracepoint(name)) {
+ printk(KERN_NOTICE "tracepoint %s busy\n", name);
+ return ERR_PTR(-EEXIST); /* Already there */
}
/*
* Using kmalloc here to allocate a variable length element. Could
@@ -234,7 +227,7 @@ static struct tracepoint_entry *add_tracepoint(const char *name)
memcpy(&e->name[0], name, name_len);
e->funcs = NULL;
e->refcount = 0;
- hlist_add_head(&e->hlist, head);
+ hash_add(tracepoint_table, &e->hlist, hash);
return e;
}
@@ -244,7 +237,7 @@ static struct tracepoint_entry *add_tracepoint(const char *name)
*/
static inline void remove_tracepoint(struct tracepoint_entry *e)
{
- hlist_del(&e->hlist);
+ hash_del(&e->hlist);
kfree(e);
}
--
1.7.12.4
^ permalink raw reply related
* [PATCH v8 05/16] mm/huge_memory: use new hashtable implementation
From: Sasha Levin @ 2012-10-30 18:46 UTC (permalink / raw)
To: torvalds
Cc: tj, akpm, linux-kernel, linux-mm, paul.gortmaker, davem, rostedt,
mingo, ebiederm, aarcange, ericvh, netdev, josh, eric.dumazet,
mathieu.desnoyers, axboe, agk, dm-devel, neilb, ccaulfie,
teigland, Trond.Myklebust, bfields, fweisbec, jesse,
venkat.x.venkatsubra, ejt, snitzer, edumazet, linux-nfs, dev,
rds-devel, lw, Sasha Levin
In-Reply-To: <1351622772-16400-1-git-send-email-levinsasha928@gmail.com>
Switch hugemem to use the new hashtable implementation. This reduces the
amount of generic unrelated code in the hugemem.
This also removes the dymanic allocation of the hash table. The size of the table is
constant so there's no point in paying the price of an extra dereference when accessing
it.
Signed-off-by: Sasha Levin <levinsasha928@gmail.com>
---
mm/huge_memory.c | 53 ++++++++++++-----------------------------------------
1 file changed, 12 insertions(+), 41 deletions(-)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 3c14a96..4b32238 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -19,6 +19,7 @@
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/migrate.h>
+#include <linux/hashtable.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.h"
@@ -59,12 +60,12 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1;
static int khugepaged(void *none);
-static int mm_slots_hash_init(void);
static int khugepaged_slab_init(void);
static void khugepaged_slab_free(void);
-#define MM_SLOTS_HASH_HEADS 1024
-static struct hlist_head *mm_slots_hash __read_mostly;
+#define MM_SLOTS_HASH_BITS 10
+static DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);
+
static struct kmem_cache *mm_slot_cache __read_mostly;
/**
@@ -545,12 +546,6 @@ static int __init hugepage_init(void)
if (err)
goto out;
- err = mm_slots_hash_init();
- if (err) {
- khugepaged_slab_free();
- goto out;
- }
-
/*
* By default disable transparent hugepages on smaller systems,
* where the extra memory used could hurt more than TLB overhead
@@ -1694,47 +1689,23 @@ static inline void free_mm_slot(struct mm_slot *mm_slot)
kmem_cache_free(mm_slot_cache, mm_slot);
}
-static int __init mm_slots_hash_init(void)
-{
- mm_slots_hash = kzalloc(MM_SLOTS_HASH_HEADS * sizeof(struct hlist_head),
- GFP_KERNEL);
- if (!mm_slots_hash)
- return -ENOMEM;
- return 0;
-}
-
-#if 0
-static void __init mm_slots_hash_free(void)
-{
- kfree(mm_slots_hash);
- mm_slots_hash = NULL;
-}
-#endif
-
static struct mm_slot *get_mm_slot(struct mm_struct *mm)
{
- struct mm_slot *mm_slot;
- struct hlist_head *bucket;
+ struct mm_slot *slot;
struct hlist_node *node;
- bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct))
- % MM_SLOTS_HASH_HEADS];
- hlist_for_each_entry(mm_slot, node, bucket, hash) {
- if (mm == mm_slot->mm)
- return mm_slot;
- }
+ hash_for_each_possible(mm_slots_hash, slot, node, hash, (unsigned long) mm)
+ if (slot->mm == mm)
+ return slot;
+
return NULL;
}
static void insert_to_mm_slots_hash(struct mm_struct *mm,
struct mm_slot *mm_slot)
{
- struct hlist_head *bucket;
-
- bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct))
- % MM_SLOTS_HASH_HEADS];
mm_slot->mm = mm;
- hlist_add_head(&mm_slot->hash, bucket);
+ hash_add(mm_slots_hash, &mm_slot->hash, (long)mm);
}
static inline int khugepaged_test_exit(struct mm_struct *mm)
@@ -1803,7 +1774,7 @@ void __khugepaged_exit(struct mm_struct *mm)
spin_lock(&khugepaged_mm_lock);
mm_slot = get_mm_slot(mm);
if (mm_slot && khugepaged_scan.mm_slot != mm_slot) {
- hlist_del(&mm_slot->hash);
+ hash_del(&mm_slot->hash);
list_del(&mm_slot->mm_node);
free = 1;
}
@@ -2252,7 +2223,7 @@ static void collect_mm_slot(struct mm_slot *mm_slot)
if (khugepaged_test_exit(mm)) {
/* free mm_slot */
- hlist_del(&mm_slot->hash);
+ hash_del(&mm_slot->hash);
list_del(&mm_slot->mm_node);
/*
--
1.7.12.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v8 04/16] workqueue: use new hashtable implementation
From: Sasha Levin @ 2012-10-30 18:46 UTC (permalink / raw)
To: torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b
Cc: snitzer-H+wXaHxf7aLQT0dZR+AlfA, neilb-l3A5Bk7waGM,
fweisbec-Re5JQEeQqe8AvxtiuMwx3w,
Trond.Myklebust-HgOvQuBEEgTQT0dZR+AlfA,
bfields-uC3wQj2KruNg9hUCZPvPmw,
paul.gortmaker-CWA4WttNNZF54TAoqtyWWQ,
dm-devel-H+wXaHxf7aLQT0dZR+AlfA, agk-H+wXaHxf7aLQT0dZR+AlfA,
aarcange-H+wXaHxf7aLQT0dZR+AlfA, rds-devel-N0ozoZBvEnrZJqsBc5GL+g,
eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w,
venkat.x.venkatsubra-QHcLZuEGTsvQT0dZR+AlfA,
ccaulfie-H+wXaHxf7aLQT0dZR+AlfA, mingo-X9Un+BFzKDI,
dev-yBygre7rU0TnMu66kgdUjQ, ericvh-Re5JQEeQqe8AvxtiuMwx3w,
josh-iaAMLnmF4UmaiuxdJuQwMA, rostedt-nx8X9YLhiw1AfugRpC6u6w,
lw-BthXqXjhjHXQFUHtdCDX3A,
mathieu.desnoyers-vg+e7yoeK/dWk0Htik3J/w, Sasha Levin,
axboe-tSWWG44O7X1aa/9Udqfwiw, linux-nfs-u79uwXL29TY76Z2rM5mHXA,
edumazet-hpIqsD4AKlfQT0dZR+AlfA, linux-mm-Bw31MaZKKs3YtjvyW6yDsg,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, ejt-H+wXaHxf7aLQT0dZR+AlfA,
ebiederm-aS9lmoZGLiVWk0Htik3J/w, tj-DgEjT+Ai2ygdnm+yROfE0A,
teigland-H+wXaHxf7aLQT0dZR+AlfA,
akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
In-Reply-To: <1351622772-16400-1-git-send-email-levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Switch workqueues to use the new hashtable implementation. This reduces the
amount of generic unrelated code in the workqueues.
Signed-off-by: Sasha Levin <levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---
kernel/workqueue.c | 86 ++++++++++--------------------------------------------
1 file changed, 15 insertions(+), 71 deletions(-)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index a1135c6..8f6e1bf 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -41,6 +41,7 @@
#include <linux/debug_locks.h>
#include <linux/lockdep.h>
#include <linux/idr.h>
+#include <linux/hashtable.h>
#include "workqueue_sched.h"
@@ -82,8 +83,6 @@ enum {
NR_WORKER_POOLS = 2, /* # worker pools per gcwq */
BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */
- BUSY_WORKER_HASH_SIZE = 1 << BUSY_WORKER_HASH_ORDER,
- BUSY_WORKER_HASH_MASK = BUSY_WORKER_HASH_SIZE - 1,
MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */
IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */
@@ -180,7 +179,7 @@ struct global_cwq {
unsigned int flags; /* L: GCWQ_* flags */
/* workers are chained either in busy_hash or pool idle_list */
- struct hlist_head busy_hash[BUSY_WORKER_HASH_SIZE];
+ DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER);
/* L: hash of busy workers */
struct worker_pool pools[NR_WORKER_POOLS];
@@ -285,8 +284,7 @@ EXPORT_SYMBOL_GPL(system_freezable_wq);
(pool) < &(gcwq)->pools[NR_WORKER_POOLS]; (pool)++)
#define for_each_busy_worker(worker, i, pos, gcwq) \
- for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++) \
- hlist_for_each_entry(worker, pos, &gcwq->busy_hash[i], hentry)
+ hash_for_each(gcwq->busy_hash, i, pos, worker, hentry)
static inline int __next_gcwq_cpu(int cpu, const struct cpumask *mask,
unsigned int sw)
@@ -857,63 +855,6 @@ static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
}
/**
- * busy_worker_head - return the busy hash head for a work
- * @gcwq: gcwq of interest
- * @work: work to be hashed
- *
- * Return hash head of @gcwq for @work.
- *
- * CONTEXT:
- * spin_lock_irq(gcwq->lock).
- *
- * RETURNS:
- * Pointer to the hash head.
- */
-static struct hlist_head *busy_worker_head(struct global_cwq *gcwq,
- struct work_struct *work)
-{
- const int base_shift = ilog2(sizeof(struct work_struct));
- unsigned long v = (unsigned long)work;
-
- /* simple shift and fold hash, do we need something better? */
- v >>= base_shift;
- v += v >> BUSY_WORKER_HASH_ORDER;
- v &= BUSY_WORKER_HASH_MASK;
-
- return &gcwq->busy_hash[v];
-}
-
-/**
- * __find_worker_executing_work - find worker which is executing a work
- * @gcwq: gcwq of interest
- * @bwh: hash head as returned by busy_worker_head()
- * @work: work to find worker for
- *
- * Find a worker which is executing @work on @gcwq. @bwh should be
- * the hash head obtained by calling busy_worker_head() with the same
- * work.
- *
- * CONTEXT:
- * spin_lock_irq(gcwq->lock).
- *
- * RETURNS:
- * Pointer to worker which is executing @work if found, NULL
- * otherwise.
- */
-static struct worker *__find_worker_executing_work(struct global_cwq *gcwq,
- struct hlist_head *bwh,
- struct work_struct *work)
-{
- struct worker *worker;
- struct hlist_node *tmp;
-
- hlist_for_each_entry(worker, tmp, bwh, hentry)
- if (worker->current_work == work)
- return worker;
- return NULL;
-}
-
-/**
* find_worker_executing_work - find worker which is executing a work
* @gcwq: gcwq of interest
* @work: work to find worker for
@@ -932,8 +873,14 @@ static struct worker *__find_worker_executing_work(struct global_cwq *gcwq,
static struct worker *find_worker_executing_work(struct global_cwq *gcwq,
struct work_struct *work)
{
- return __find_worker_executing_work(gcwq, busy_worker_head(gcwq, work),
- work);
+ struct worker *worker;
+ struct hlist_node *tmp;
+
+ hash_for_each_possible(gcwq->busy_hash, worker, tmp, hentry, (unsigned long)work)
+ if (worker->current_work == work)
+ return worker;
+
+ return NULL;
}
/**
@@ -2160,7 +2107,6 @@ __acquires(&gcwq->lock)
struct cpu_workqueue_struct *cwq = get_work_cwq(work);
struct worker_pool *pool = worker->pool;
struct global_cwq *gcwq = pool->gcwq;
- struct hlist_head *bwh = busy_worker_head(gcwq, work);
bool cpu_intensive = cwq->wq->flags & WQ_CPU_INTENSIVE;
work_func_t f = work->func;
int work_color;
@@ -2192,7 +2138,7 @@ __acquires(&gcwq->lock)
* already processing the work. If so, defer the work to the
* currently executing one.
*/
- collision = __find_worker_executing_work(gcwq, bwh, work);
+ collision = find_worker_executing_work(gcwq, work);
if (unlikely(collision)) {
move_linked_works(work, &collision->scheduled, NULL);
return;
@@ -2200,7 +2146,7 @@ __acquires(&gcwq->lock)
/* claim and dequeue */
debug_work_deactivate(work);
- hlist_add_head(&worker->hentry, bwh);
+ hash_add(gcwq->busy_hash, &worker->hentry, (unsigned long)worker);
worker->current_work = work;
worker->current_cwq = cwq;
work_color = get_work_color(work);
@@ -2258,7 +2204,7 @@ __acquires(&gcwq->lock)
worker_clr_flags(worker, WORKER_CPU_INTENSIVE);
/* we're done with it, release */
- hlist_del_init(&worker->hentry);
+ hash_del(&worker->hentry);
worker->current_work = NULL;
worker->current_cwq = NULL;
cwq_dec_nr_in_flight(cwq, work_color);
@@ -3823,7 +3769,6 @@ out_unlock:
static int __init init_workqueues(void)
{
unsigned int cpu;
- int i;
/* make sure we have enough bits for OFFQ CPU number */
BUILD_BUG_ON((1LU << (BITS_PER_LONG - WORK_OFFQ_CPU_SHIFT)) <
@@ -3841,8 +3786,7 @@ static int __init init_workqueues(void)
gcwq->cpu = cpu;
gcwq->flags |= GCWQ_DISASSOCIATED;
- for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++)
- INIT_HLIST_HEAD(&gcwq->busy_hash[i]);
+ hash_init(gcwq->busy_hash);
for_each_worker_pool(pool, gcwq) {
pool->gcwq = gcwq;
--
1.7.12.4
^ permalink raw reply related
* [PATCH v8 03/16] mm,ksm: use new hashtable implementation
From: Sasha Levin @ 2012-10-30 18:45 UTC (permalink / raw)
To: torvalds
Cc: tj, akpm, linux-kernel, linux-mm, paul.gortmaker, davem, rostedt,
mingo, ebiederm, aarcange, ericvh, netdev, josh, eric.dumazet,
mathieu.desnoyers, axboe, agk, dm-devel, neilb, ccaulfie,
teigland, Trond.Myklebust, bfields, fweisbec, jesse,
venkat.x.venkatsubra, ejt, snitzer, edumazet, linux-nfs, dev,
rds-devel, lw, Sasha Levin
In-Reply-To: <1351622772-16400-1-git-send-email-levinsasha928@gmail.com>
Switch ksm to use the new hashtable implementation. This reduces the amount of
generic unrelated code in the ksm module.
Signed-off-by: Sasha Levin <levinsasha928@gmail.com>
---
mm/ksm.c | 31 +++++++++++++------------------
1 file changed, 13 insertions(+), 18 deletions(-)
diff --git a/mm/ksm.c b/mm/ksm.c
index 31ae5ea..751e328 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -33,7 +33,7 @@
#include <linux/mmu_notifier.h>
#include <linux/swap.h>
#include <linux/ksm.h>
-#include <linux/hash.h>
+#include <linux/hashtable.h>
#include <linux/freezer.h>
#include <linux/oom.h>
@@ -156,9 +156,8 @@ struct rmap_item {
static struct rb_root root_stable_tree = RB_ROOT;
static struct rb_root root_unstable_tree = RB_ROOT;
-#define MM_SLOTS_HASH_SHIFT 10
-#define MM_SLOTS_HASH_HEADS (1 << MM_SLOTS_HASH_SHIFT)
-static struct hlist_head mm_slots_hash[MM_SLOTS_HASH_HEADS];
+#define MM_SLOTS_HASH_BITS 10
+static DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);
static struct mm_slot ksm_mm_head = {
.mm_list = LIST_HEAD_INIT(ksm_mm_head.mm_list),
@@ -275,26 +274,21 @@ static inline void free_mm_slot(struct mm_slot *mm_slot)
static struct mm_slot *get_mm_slot(struct mm_struct *mm)
{
- struct mm_slot *mm_slot;
- struct hlist_head *bucket;
struct hlist_node *node;
+ struct mm_slot *slot;
+
+ hash_for_each_possible(mm_slots_hash, slot, node, link, (unsigned long)mm)
+ if (slot->mm == mm)
+ return slot;
- bucket = &mm_slots_hash[hash_ptr(mm, MM_SLOTS_HASH_SHIFT)];
- hlist_for_each_entry(mm_slot, node, bucket, link) {
- if (mm == mm_slot->mm)
- return mm_slot;
- }
return NULL;
}
static void insert_to_mm_slots_hash(struct mm_struct *mm,
struct mm_slot *mm_slot)
{
- struct hlist_head *bucket;
-
- bucket = &mm_slots_hash[hash_ptr(mm, MM_SLOTS_HASH_SHIFT)];
mm_slot->mm = mm;
- hlist_add_head(&mm_slot->link, bucket);
+ hash_add(mm_slots_hash, &mm_slot->link, (unsigned long)mm);
}
static inline int in_stable_tree(struct rmap_item *rmap_item)
@@ -647,7 +641,7 @@ static int unmerge_and_remove_all_rmap_items(void)
ksm_scan.mm_slot = list_entry(mm_slot->mm_list.next,
struct mm_slot, mm_list);
if (ksm_test_exit(mm)) {
- hlist_del(&mm_slot->link);
+ hash_del(&mm_slot->link);
list_del(&mm_slot->mm_list);
spin_unlock(&ksm_mmlist_lock);
@@ -1392,7 +1386,7 @@ next_mm:
* or when all VM_MERGEABLE areas have been unmapped (and
* mmap_sem then protects against race with MADV_MERGEABLE).
*/
- hlist_del(&slot->link);
+ hash_del(&slot->link);
list_del(&slot->mm_list);
spin_unlock(&ksm_mmlist_lock);
@@ -1559,7 +1553,7 @@ void __ksm_exit(struct mm_struct *mm)
mm_slot = get_mm_slot(mm);
if (mm_slot && ksm_scan.mm_slot != mm_slot) {
if (!mm_slot->rmap_list) {
- hlist_del(&mm_slot->link);
+ hash_del(&mm_slot->link);
list_del(&mm_slot->mm_list);
easy_to_free = 1;
} else {
@@ -2038,6 +2032,7 @@ static int __init ksm_init(void)
*/
hotplug_memory_notifier(ksm_memory_callback, 100);
#endif
+
return 0;
out_free:
--
1.7.12.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v8 02/16] userns: use new hashtable implementation
From: Sasha Levin @ 2012-10-30 18:45 UTC (permalink / raw)
To: torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b
Cc: snitzer-H+wXaHxf7aLQT0dZR+AlfA, neilb-l3A5Bk7waGM,
fweisbec-Re5JQEeQqe8AvxtiuMwx3w,
Trond.Myklebust-HgOvQuBEEgTQT0dZR+AlfA,
bfields-uC3wQj2KruNg9hUCZPvPmw,
paul.gortmaker-CWA4WttNNZF54TAoqtyWWQ,
dm-devel-H+wXaHxf7aLQT0dZR+AlfA, agk-H+wXaHxf7aLQT0dZR+AlfA,
aarcange-H+wXaHxf7aLQT0dZR+AlfA, rds-devel-N0ozoZBvEnrZJqsBc5GL+g,
eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w,
venkat.x.venkatsubra-QHcLZuEGTsvQT0dZR+AlfA,
ccaulfie-H+wXaHxf7aLQT0dZR+AlfA, mingo-X9Un+BFzKDI,
dev-yBygre7rU0TnMu66kgdUjQ, ericvh-Re5JQEeQqe8AvxtiuMwx3w,
josh-iaAMLnmF4UmaiuxdJuQwMA, rostedt-nx8X9YLhiw1AfugRpC6u6w,
lw-BthXqXjhjHXQFUHtdCDX3A,
mathieu.desnoyers-vg+e7yoeK/dWk0Htik3J/w, Sasha Levin,
axboe-tSWWG44O7X1aa/9Udqfwiw, linux-nfs-u79uwXL29TY76Z2rM5mHXA,
edumazet-hpIqsD4AKlfQT0dZR+AlfA, linux-mm-Bw31MaZKKs3YtjvyW6yDsg,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, ejt-H+wXaHxf7aLQT0dZR+AlfA,
ebiederm-aS9lmoZGLiVWk0Htik3J/w, tj-DgEjT+Ai2ygdnm+yROfE0A,
teigland-H+wXaHxf7aLQT0dZR+AlfA,
akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
In-Reply-To: <1351622772-16400-1-git-send-email-levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Switch to using the new hashtable implementation to store user structs.
This reduces the amount of generic unrelated code in kernel/user.c.
Signed-off-by: Sasha Levin <levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---
kernel/user.c | 33 ++++++++++++---------------------
1 file changed, 12 insertions(+), 21 deletions(-)
diff --git a/kernel/user.c b/kernel/user.c
index 750acff..f010389 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -16,6 +16,7 @@
#include <linux/interrupt.h>
#include <linux/export.h>
#include <linux/user_namespace.h>
+#include <linux/hashtable.h>
/*
* userns count is 1 for root user, 1 for init_uts_ns,
@@ -60,13 +61,9 @@ EXPORT_SYMBOL_GPL(init_user_ns);
*/
#define UIDHASH_BITS (CONFIG_BASE_SMALL ? 3 : 7)
-#define UIDHASH_SZ (1 << UIDHASH_BITS)
-#define UIDHASH_MASK (UIDHASH_SZ - 1)
-#define __uidhashfn(uid) (((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK)
-#define uidhashentry(uid) (uidhash_table + __uidhashfn((__kuid_val(uid))))
static struct kmem_cache *uid_cachep;
-struct hlist_head uidhash_table[UIDHASH_SZ];
+static DEFINE_HASHTABLE(uidhash_table, UIDHASH_BITS);
/*
* The uidhash_lock is mostly taken from process context, but it is
@@ -92,22 +89,22 @@ struct user_struct root_user = {
/*
* These routines must be called with the uidhash spinlock held!
*/
-static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
+static void uid_hash_insert(struct user_struct *up)
{
- hlist_add_head(&up->uidhash_node, hashent);
+ hash_add(uidhash_table, &up->uidhash_node, __kuid_val(up->uid));
}
static void uid_hash_remove(struct user_struct *up)
{
- hlist_del_init(&up->uidhash_node);
+ hash_del(&up->uidhash_node);
}
-static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent)
+static struct user_struct *uid_hash_find(kuid_t uid)
{
struct user_struct *user;
struct hlist_node *h;
- hlist_for_each_entry(user, h, hashent, uidhash_node) {
+ hash_for_each_possible(uidhash_table, user, h, uidhash_node, __kuid_val(uid)) {
if (uid_eq(user->uid, uid)) {
atomic_inc(&user->__count);
return user;
@@ -143,7 +140,7 @@ struct user_struct *find_user(kuid_t uid)
unsigned long flags;
spin_lock_irqsave(&uidhash_lock, flags);
- ret = uid_hash_find(uid, uidhashentry(uid));
+ ret = uid_hash_find(uid);
spin_unlock_irqrestore(&uidhash_lock, flags);
return ret;
}
@@ -164,11 +161,10 @@ void free_uid(struct user_struct *up)
struct user_struct *alloc_uid(kuid_t uid)
{
- struct hlist_head *hashent = uidhashentry(uid);
struct user_struct *up, *new;
spin_lock_irq(&uidhash_lock);
- up = uid_hash_find(uid, hashent);
+ up = uid_hash_find(uid);
spin_unlock_irq(&uidhash_lock);
if (!up) {
@@ -184,13 +180,13 @@ struct user_struct *alloc_uid(kuid_t uid)
* on adding the same user already..
*/
spin_lock_irq(&uidhash_lock);
- up = uid_hash_find(uid, hashent);
+ up = uid_hash_find(uid);
if (up) {
key_put(new->uid_keyring);
key_put(new->session_keyring);
kmem_cache_free(uid_cachep, new);
} else {
- uid_hash_insert(new, hashent);
+ uid_hash_insert(new);
up = new;
}
spin_unlock_irq(&uidhash_lock);
@@ -204,17 +200,12 @@ out_unlock:
static int __init uid_cache_init(void)
{
- int n;
-
uid_cachep = kmem_cache_create("uid_cache", sizeof(struct user_struct),
0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
- for(n = 0; n < UIDHASH_SZ; ++n)
- INIT_HLIST_HEAD(uidhash_table + n);
-
/* Insert the root user immediately (init already runs as root) */
spin_lock_irq(&uidhash_lock);
- uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID));
+ uid_hash_insert(&root_user);
spin_unlock_irq(&uidhash_lock);
return 0;
--
1.7.12.4
^ permalink raw reply related
* [PATCH v8 01/16] hashtable: introduce a small and naive hashtable
From: Sasha Levin @ 2012-10-30 18:45 UTC (permalink / raw)
To: torvalds
Cc: tj, akpm, linux-kernel, linux-mm, paul.gortmaker, davem, rostedt,
mingo, ebiederm, aarcange, ericvh, netdev, josh, eric.dumazet,
mathieu.desnoyers, axboe, agk, dm-devel, neilb, ccaulfie,
teigland, Trond.Myklebust, bfields, fweisbec, jesse,
venkat.x.venkatsubra, ejt, snitzer, edumazet, linux-nfs, dev,
rds-devel, lw, Sasha Levin
This hashtable implementation is using hlist buckets to provide a simple
hashtable to prevent it from getting reimplemented all over the kernel.
Signed-off-by: Sasha Levin <levinsasha928@gmail.com>
---
Changes from v8:
- Addressed comments from Tejun Heo and Mathieu Desnoyers.
include/linux/hashtable.h | 196 ++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 196 insertions(+)
create mode 100644 include/linux/hashtable.h
diff --git a/include/linux/hashtable.h b/include/linux/hashtable.h
new file mode 100644
index 0000000..3c1a9cb
--- /dev/null
+++ b/include/linux/hashtable.h
@@ -0,0 +1,196 @@
+/*
+ * Statically sized hash table implementation
+ * (C) 2012 Sasha Levin <levinsasha928@gmail.com>
+ */
+
+#ifndef _LINUX_HASHTABLE_H
+#define _LINUX_HASHTABLE_H
+
+#include <linux/list.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/hash.h>
+#include <linux/rculist.h>
+
+#define DEFINE_HASHTABLE(name, bits) \
+ struct hlist_head name[1 << (bits)] = \
+ { [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT }
+
+#define DECLARE_HASHTABLE(name, bits) \
+ struct hlist_head name[1 << (bits)]
+
+#define HASH_SIZE(name) (ARRAY_SIZE(name))
+#define HASH_BITS(name) ilog2(HASH_SIZE(name))
+
+/* Use hash_32 when possible to allow for fast 32bit hashing in 64bit kernels. */
+#define hash_min(val, bits) \
+({ \
+ sizeof(val) <= 4 ? \
+ hash_32(val, bits) : \
+ hash_long(val, bits); \
+})
+
+static inline void __hash_init(struct hlist_head *ht, unsigned int sz)
+{
+ unsigned int i;
+
+ for (i = 0; i < sz; i++)
+ INIT_HLIST_HEAD(&ht[i]);
+}
+
+/**
+ * hash_init - initialize a hash table
+ * @hashtable: hashtable to be initialized
+ *
+ * Calculates the size of the hashtable from the given parameter, otherwise
+ * same as hash_init_size.
+ *
+ * This has to be a macro since HASH_BITS() will not work on pointers since
+ * it calculates the size during preprocessing.
+ */
+#define hash_init(hashtable) __hash_init(hashtable, HASH_SIZE(hashtable))
+
+/**
+ * hash_add - add an object to a hashtable
+ * @hashtable: hashtable to add to
+ * @node: the &struct hlist_node of the object to be added
+ * @key: the key of the object to be added
+ */
+#define hash_add(hashtable, node, key) \
+ hlist_add_head(node, &hashtable[hash_min(key, HASH_BITS(hashtable))])
+
+/**
+ * hash_add_rcu - add an object to a rcu enabled hashtable
+ * @hashtable: hashtable to add to
+ * @node: the &struct hlist_node of the object to be added
+ * @key: the key of the object to be added
+ */
+#define hash_add_rcu(hashtable, node, key) \
+ hlist_add_head_rcu(node, &hashtable[hash_min(key, HASH_BITS(hashtable))])
+
+/**
+ * hash_hashed - check whether an object is in any hashtable
+ * @node: the &struct hlist_node of the object to be checked
+ */
+static inline bool hash_hashed(struct hlist_node *node)
+{
+ return !hlist_unhashed(node);
+}
+
+static inline bool __hash_empty(struct hlist_head *ht, unsigned int sz)
+{
+ unsigned int i;
+
+ for (i = 0; i < sz; i++)
+ if (!hlist_empty(&ht[i]))
+ return false;
+
+ return true;
+}
+
+/**
+ * hash_empty - check whether a hashtable is empty
+ * @hashtable: hashtable to check
+ *
+ * This has to be a macro since HASH_BITS() will not work on pointers since
+ * it calculates the size during preprocessing.
+ */
+#define hash_empty(hashtable) __hash_empty(hashtable, HASH_SIZE(hashtable))
+
+/**
+ * hash_del - remove an object from a hashtable
+ * @node: &struct hlist_node of the object to remove
+ */
+static inline void hash_del(struct hlist_node *node)
+{
+ hlist_del_init(node);
+}
+
+/**
+ * hash_del_rcu - remove an object from a rcu enabled hashtable
+ * @node: &struct hlist_node of the object to remove
+ */
+static inline void hash_del_rcu(struct hlist_node *node)
+{
+ hlist_del_init_rcu(node);
+}
+
+/**
+ * hash_for_each - iterate over a hashtable
+ * @name: hashtable to iterate
+ * @bkt: integer to use as bucket loop cursor
+ * @node: the &struct list_head to use as a loop cursor for each entry
+ * @obj: the type * to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ */
+#define hash_for_each(name, bkt, node, obj, member) \
+ for ((bkt) = 0, node = NULL; node == NULL && (bkt) < HASH_SIZE(name); (bkt)++)\
+ hlist_for_each_entry(obj, node, &name[bkt], member)
+
+/**
+ * hash_for_each_rcu - iterate over a rcu enabled hashtable
+ * @name: hashtable to iterate
+ * @bkt: integer to use as bucket loop cursor
+ * @node: the &struct list_head to use as a loop cursor for each entry
+ * @obj: the type * to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ */
+#define hash_for_each_rcu(name, bkt, node, obj, member) \
+ for ((bkt) = 0, node = NULL; node == NULL && (bkt) < HASH_SIZE(name); (bkt)++)\
+ hlist_for_each_entry_rcu(obj, node, &name[bkt], member)
+
+/**
+ * hash_for_each_safe - iterate over a hashtable safe against removal of
+ * hash entry
+ * @name: hashtable to iterate
+ * @bkt: integer to use as bucket loop cursor
+ * @node: the &struct list_head to use as a loop cursor for each entry
+ * @tmp: a &struct used for temporary storage
+ * @obj: the type * to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ */
+#define hash_for_each_safe(name, bkt, node, tmp, obj, member) \
+ for ((bkt) = 0, node = NULL; node == NULL && (bkt) < HASH_SIZE(name); (bkt)++)\
+ hlist_for_each_entry_safe(obj, node, tmp, &name[bkt], member)
+
+/**
+ * hash_for_each_possible - iterate over all possible objects hashing to the
+ * same bucket
+ * @name: hashtable to iterate
+ * @obj: the type * to use as a loop cursor for each entry
+ * @node: the &struct list_head to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ * @key: the key of the objects to iterate over
+ */
+#define hash_for_each_possible(name, obj, node, member, key) \
+ hlist_for_each_entry(obj, node, &name[hash_min(key, HASH_BITS(name))], member)
+
+/**
+ * hash_for_each_possible_rcu - iterate over all possible objects hashing to the
+ * same bucket in an rcu enabled hashtable
+ * in a rcu enabled hashtable
+ * @name: hashtable to iterate
+ * @obj: the type * to use as a loop cursor for each entry
+ * @node: the &struct list_head to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ * @key: the key of the objects to iterate over
+ */
+#define hash_for_each_possible_rcu(name, obj, node, member, key) \
+ hlist_for_each_entry_rcu(obj, node, &name[hash_min(key, HASH_BITS(name))], member)
+
+/**
+ * hash_for_each_possible_safe - iterate over all possible objects hashing to the
+ * same bucket safe against removals
+ * @name: hashtable to iterate
+ * @obj: the type * to use as a loop cursor for each entry
+ * @node: the &struct list_head to use as a loop cursor for each entry
+ * @tmp: a &struct used for temporary storage
+ * @member: the name of the hlist_node within the struct
+ * @key: the key of the objects to iterate over
+ */
+#define hash_for_each_possible_safe(name, obj, node, tmp, member, key) \
+ hlist_for_each_entry_safe(obj, node, tmp, \
+ &name[hash_min(key, HASH_BITS(name))], member)
+
+
+#endif
--
1.7.12.4
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* Re: [PATCH v3 06/10] net/macb: clean up ring buffer logic
From: Håvard Skinnemoen @ 2012-10-30 18:22 UTC (permalink / raw)
To: David Laight
Cc: Nicolas Ferre, netdev, davem, bhutchings, linux-arm-kernel,
plagnioj, patrice.vilchez, linux-kernel, manabian
In-Reply-To: <AE90C24D6B3A694183C094C60CF0A2F6026B707D@saturn3.aculab.com>
On Tue, Oct 30, 2012 at 4:12 AM, David Laight <David.Laight@aculab.com> wrote:
>> Instead of masking head and tail every time we increment them, just let them
>> wrap through UINT_MAX and mask them when subscripting. Add simple accessor
>> functions to do the subscripting properly to minimize the chances of messing
>> this up.
> ...
>> +static unsigned int macb_tx_ring_avail(struct macb *bp)
>> +{
>> + return TX_RING_SIZE - (bp->tx_head - bp->tx_tail);
>> +}
>
> That one doesn't look quite right to me.
> Surely it should be masking with 'TX_RING_SIZE - 1'
Why is that? head and tail can never be more than TX_RING_SIZE apart,
so it shouldn't make any difference.
Havard
^ permalink raw reply
* Re: [PATCH v2 2/3] pppoatm: fix race condition with destroying of vcc
From: Krzysztof Mazur @ 2012-10-30 18:20 UTC (permalink / raw)
To: Chas Williams (CONTRACTOR); +Cc: davem, dwmw2, netdev, linux-kernel
In-Reply-To: <201210301426.q9UEQkI7007209@thirdoffive.cmf.nrl.navy.mil>
On Tue, Oct 30, 2012 at 10:26:46AM -0400, Chas Williams (CONTRACTOR) wrote:
> In message <1350926091-12642-2-git-send-email-krzysiek@podlesie.net>,Krzysztof Mazur writes:
>
> as i recall from way back, this shouldnt be necessary. closing a vcc
> for an attached protocol isnt supposed to require addtional locking
> or synchronization.
Such locking is already used by vcc_sendmsg() and I think we should do here
exacly what vcc_sendmsg() does.
>
> vcc_release() locks the socket and vcc_destroy_socket() calls the device's
> vcc close routine and pushes a NULL skb to the attached protocol.
> this NULL push is supposed to let the attached protocol that no more
> sends and recvs can be handled.
>
> that said, the order for the device vcc close and push does seem
> reversed. since i imagine there could be a pending pppoatm_send()
> during this interval. the push of the NULL skb is allowed to wait for
> the subprotocol to finish its cleanup/shutdown.
Yes, this problem can be probably fixed by reversing close and push
and adding some synchronization to pppoatm_unassign_vcc(), but I think
we need that locking anyway, for instance for synchronization for
checking and incrementing sk->sk_wmem_alloc, between pppoatm_send()
and vcc_sendmsg().
Thanks.
Krzysiek
^ permalink raw reply
* [PATCH 1/1] smsc75xx: add wol support for more frame types
From: Steve Glendinning @ 2012-10-30 17:46 UTC (permalink / raw)
To: netdev; +Cc: Steve Glendinning
In-Reply-To: <1351619192-11022-1-git-send-email-steve.glendinning@shawell.net>
This patch adds support for wol wakeup on unicast, broadcast,
multicast and arp frames.
Signed-off-by: Steve Glendinning <steve.glendinning@shawell.net>
---
drivers/net/usb/Kconfig | 2 +
drivers/net/usb/smsc75xx.c | 155 ++++++++++++++++++++++++++++++++++----------
2 files changed, 124 insertions(+), 33 deletions(-)
diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index 2ab8043..2118ca2 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -248,6 +248,8 @@ config USB_NET_DM9601
config USB_NET_SMSC75XX
tristate "SMSC LAN75XX based USB 2.0 gigabit ethernet devices"
depends on USB_USBNET
+ select BITREVERSE
+ select CRC16
select CRC32
help
This option adds support for SMSC LAN95XX based USB 2.0
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index 1baa53a..85d70c2 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -26,6 +26,8 @@
#include <linux/ethtool.h>
#include <linux/mii.h>
#include <linux/usb.h>
+#include <linux/bitrev.h>
+#include <linux/crc16.h>
#include <linux/crc32.h>
#include <linux/usb/usbnet.h>
#include <linux/slab.h>
@@ -52,7 +54,8 @@
#define USB_PRODUCT_ID_LAN7500 (0x7500)
#define USB_PRODUCT_ID_LAN7505 (0x7505)
#define RXW_PADDING 2
-#define SUPPORTED_WAKE (WAKE_MAGIC)
+#define SUPPORTED_WAKE (WAKE_UCAST | WAKE_BCAST | \
+ WAKE_MCAST | WAKE_ARP | WAKE_MAGIC)
#define check_warn(ret, fmt, args...) \
({ if (ret < 0) netdev_warn(dev->net, fmt, ##args); })
@@ -1143,6 +1146,36 @@ static void smsc75xx_unbind(struct usbnet *dev, struct usb_interface *intf)
}
}
+static u16 smsc_crc(const u8 *buffer, size_t len)
+{
+ return bitrev16(crc16(0xFFFF, buffer, len));
+}
+
+static int smsc75xx_write_wuff(struct usbnet *dev, int filter, u32 wuf_cfg,
+ u32 wuf_mask1)
+{
+ int cfg_base = WUF_CFGX + filter * 4;
+ int mask_base = WUF_MASKX + filter * 16;
+ int ret;
+
+ ret = smsc75xx_write_reg(dev, cfg_base, wuf_cfg);
+ check_warn_return(ret, "Error writing WUF_CFGX");
+
+ ret = smsc75xx_write_reg(dev, mask_base, wuf_mask1);
+ check_warn_return(ret, "Error writing WUF_MASKX");
+
+ ret = smsc75xx_write_reg(dev, mask_base + 4, 0);
+ check_warn_return(ret, "Error writing WUF_MASKX");
+
+ ret = smsc75xx_write_reg(dev, mask_base + 8, 0);
+ check_warn_return(ret, "Error writing WUF_MASKX");
+
+ ret = smsc75xx_write_reg(dev, mask_base + 12, 0);
+ check_warn_return(ret, "Error writing WUF_MASKX");
+
+ return 0;
+}
+
static int smsc75xx_suspend(struct usb_interface *intf, pm_message_t message)
{
struct usbnet *dev = usb_get_intfdata(intf);
@@ -1187,42 +1220,107 @@ static int smsc75xx_suspend(struct usb_interface *intf, pm_message_t message)
return 0;
}
- if (pdata->wolopts & WAKE_MAGIC) {
- /* clear any pending magic packet status */
+ if (pdata->wolopts & (WAKE_MCAST | WAKE_ARP)) {
+ int i, filter = 0;
+
+ /* disable all filters */
+ for (i = 0; i < WUF_NUM; i++) {
+ ret = smsc75xx_write_reg(dev, WUF_CFGX + i * 4, 0);
+ check_warn_return(ret, "Error writing WUF_CFGX");
+ }
+
+ if (pdata->wolopts & WAKE_MCAST) {
+ const u8 mcast[] = {0x01, 0x00, 0x5E};
+ netdev_info(dev->net, "enabling multicast detection");
+
+ val = WUF_CFGX_EN | WUF_CFGX_ATYPE_MULTICAST
+ | smsc_crc(mcast, 3);
+ ret = smsc75xx_write_wuff(dev, filter++, val, 0x0007);
+ check_warn_return(ret, "Error writing wakeup filter");
+ }
+
+ if (pdata->wolopts & WAKE_ARP) {
+ const u8 arp[] = {0x08, 0x06};
+ netdev_info(dev->net, "enabling ARP detection");
+
+ val = WUF_CFGX_EN | WUF_CFGX_ATYPE_ALL | (0x0C << 16)
+ | smsc_crc(arp, 2);
+ ret = smsc75xx_write_wuff(dev, filter++, val, 0x0003);
+ check_warn_return(ret, "Error writing wakeup filter");
+ }
+
+ /* clear any pending pattern match packet status */
+ ret = smsc75xx_read_reg(dev, WUCSR, &val);
+ check_warn_return(ret, "Error reading WUCSR");
+
+ val |= WUCSR_WUFR;
+
+ ret = smsc75xx_write_reg(dev, WUCSR, val);
+ check_warn_return(ret, "Error writing WUCSR");
+
+ netdev_info(dev->net, "enabling packet match detection");
+ ret = smsc75xx_read_reg(dev, WUCSR, &val);
+ check_warn_return(ret, "Error reading WUCSR");
+
+ val |= WUCSR_WUEN;
+
+ ret = smsc75xx_write_reg(dev, WUCSR, val);
+ check_warn_return(ret, "Error writing WUCSR");
+ } else {
+ netdev_info(dev->net, "disabling packet match detection");
ret = smsc75xx_read_reg(dev, WUCSR, &val);
check_warn_return(ret, "Error reading WUCSR");
- val |= WUCSR_MPR;
+ val &= ~WUCSR_WUEN;
ret = smsc75xx_write_reg(dev, WUCSR, val);
check_warn_return(ret, "Error writing WUCSR");
}
- /* enable/disable magic packup wake */
+ /* disable magic, bcast & unicast wakeup sources */
ret = smsc75xx_read_reg(dev, WUCSR, &val);
check_warn_return(ret, "Error reading WUCSR");
+ val &= ~(WUCSR_MPEN | WUCSR_BCST_EN | WUCSR_PFDA_EN);
+
+ ret = smsc75xx_write_reg(dev, WUCSR, val);
+ check_warn_return(ret, "Error writing WUCSR");
+
if (pdata->wolopts & WAKE_MAGIC) {
netdev_info(dev->net, "enabling magic packet wakeup");
- val |= WUCSR_MPEN;
- } else {
- netdev_info(dev->net, "disabling magic packet wakeup");
- val &= ~WUCSR_MPEN;
+ ret = smsc75xx_read_reg(dev, WUCSR, &val);
+ check_warn_return(ret, "Error reading WUCSR");
+
+ /* clear any pending magic packet status */
+ val |= WUCSR_MPR | WUCSR_MPEN;
+
+ ret = smsc75xx_write_reg(dev, WUCSR, val);
+ check_warn_return(ret, "Error writing WUCSR");
}
- ret = smsc75xx_write_reg(dev, WUCSR, val);
- check_warn_return(ret, "Error writing WUCSR");
+ if (pdata->wolopts & WAKE_BCAST) {
+ netdev_info(dev->net, "enabling broadcast detection");
+ ret = smsc75xx_read_reg(dev, WUCSR, &val);
+ check_warn_return(ret, "Error reading WUCSR");
- /* enable wol wakeup source */
- ret = smsc75xx_read_reg(dev, PMT_CTL, &val);
- check_warn_return(ret, "Error reading PMT_CTL");
+ val |= WUCSR_BCAST_FR | WUCSR_BCST_EN;
- val |= PMT_CTL_WOL_EN;
+ ret = smsc75xx_write_reg(dev, WUCSR, val);
+ check_warn_return(ret, "Error writing WUCSR");
+ }
- ret = smsc75xx_write_reg(dev, PMT_CTL, val);
- check_warn_return(ret, "Error writing PMT_CTL");
+ if (pdata->wolopts & WAKE_UCAST) {
+ netdev_info(dev->net, "enabling unicast detection");
+ ret = smsc75xx_read_reg(dev, WUCSR, &val);
+ check_warn_return(ret, "Error reading WUCSR");
+
+ val |= WUCSR_WUFR | WUCSR_PFDA_EN;
- /* enable receiver */
+ ret = smsc75xx_write_reg(dev, WUCSR, val);
+ check_warn_return(ret, "Error writing WUCSR");
+ }
+
+ /* enable receiver to enable frame reception */
ret = smsc75xx_read_reg(dev, MAC_RX, &val);
check_warn_return(ret, "Failed to read MAC_RX: %d", ret);
@@ -1237,22 +1335,12 @@ static int smsc75xx_suspend(struct usb_interface *intf, pm_message_t message)
ret = smsc75xx_read_reg(dev, PMT_CTL, &val);
check_warn_return(ret, "Error reading PMT_CTL");
- val &= (~(PMT_CTL_SUS_MODE | PMT_CTL_WUPS | PMT_CTL_PHY_RST));
- val |= PMT_CTL_SUS_MODE_0;
-
- ret = smsc75xx_write_reg(dev, PMT_CTL, val);
- check_warn_return(ret, "Error writing PMT_CTL");
+ val &= (~(PMT_CTL_SUS_MODE | PMT_CTL_PHY_RST));
+ val |= PMT_CTL_SUS_MODE_0 | PMT_CTL_WOL_EN | PMT_CTL_WUPS;
- /* clear wol status */
- val &= ~PMT_CTL_WUPS;
- val |= PMT_CTL_WUPS_WOL;
ret = smsc75xx_write_reg(dev, PMT_CTL, val);
check_warn_return(ret, "Error writing PMT_CTL");
- /* read back PMT_CTL */
- ret = smsc75xx_read_reg(dev, PMT_CTL, &val);
- check_warn_return(ret, "Error reading PMT_CTL");
-
smsc75xx_set_feature(dev, USB_DEVICE_REMOTE_WAKEUP);
return 0;
@@ -1265,16 +1353,17 @@ static int smsc75xx_resume(struct usb_interface *intf)
int ret;
u32 val;
- if (pdata->wolopts & WAKE_MAGIC) {
+ if (pdata->wolopts) {
netdev_info(dev->net, "resuming from SUSPEND0");
smsc75xx_clear_feature(dev, USB_DEVICE_REMOTE_WAKEUP);
- /* Disable magic packup wake */
+ /* Disable wakeup sources */
ret = smsc75xx_read_reg(dev, WUCSR, &val);
check_warn_return(ret, "Error reading WUCSR");
- val &= ~WUCSR_MPEN;
+ val &= ~(WUCSR_WUEN | WUCSR_MPEN | WUCSR_PFDA_EN
+ | WUCSR_BCST_EN);
ret = smsc75xx_write_reg(dev, WUCSR, val);
check_warn_return(ret, "Error writing WUCSR");
--
1.7.10.4
^ permalink raw reply related
* [PATCH 0/1] smsc75xx: wol enhancements
From: Steve Glendinning @ 2012-10-30 17:46 UTC (permalink / raw)
To: netdev; +Cc: Steve Glendinning
This patch adds support for more WOL frame types to smsc75xx,
similarly to a patch recently submitted for smsc95xx.
Please review and consider for inclusion into net-next.
Steve Glendinning (1):
smsc75xx: add wol support for more frame types
drivers/net/usb/Kconfig | 2 +
drivers/net/usb/smsc75xx.c | 155 ++++++++++++++++++++++++++++++++++----------
2 files changed, 124 insertions(+), 33 deletions(-)
--
1.7.10.4
^ permalink raw reply
* Re: [PATCH] net: allow configuration of the size of page in __netdev_alloc_frag
From: Konrad Rzeszutek Wilk @ 2012-10-30 16:53 UTC (permalink / raw)
To: Eric Dumazet
Cc: Ian Campbell, netdev@vger.kernel.org, Eric Dumazet,
xen-devel@lists.xen.org
In-Reply-To: <1351097000.6537.109.camel@edumazet-glaptop>
[-- Attachment #1: Type: text/plain, Size: 2625 bytes --]
On Wed, Oct 24, 2012 at 06:43:20PM +0200, Eric Dumazet wrote:
> On Wed, 2012-10-24 at 17:22 +0100, Ian Campbell wrote:
> > On Wed, 2012-10-24 at 16:21 +0100, Eric Dumazet wrote:
>
> > > If you really have such problems, why locally generated TCP traffic
> > > doesnt also have it ?
> >
> > I think it does. The reason I noticed the original problem was that ssh
> > to the machine was virtually (no pun intended) unusable.
> >
> > > Your patch doesnt touch sk_page_frag_refill(), does it ?
> >
> > That's right. It doesn't. When is (sk->sk_allocation & __GFP_WAIT) true?
> > Is it possible I'm just not hitting that case?
> >
>
> I hope not. GFP_KERNEL has __GFP_WAIT.
>
> > Is it possible that this only affects certain traffic patterns (I only
> > really tried ssh/scp and ping)? Or perhaps its just that the swiotlb is
> > only broken in one corner case and not the other.
>
> Could you try a netperf -t TCP_STREAM ?
For fun I did a couple of tests - I setup two machines (one r8168, the other
e1000e) and tried to do netperf/netserver. Both of them are running a baremetal
kernel and one of them has 'iommu=soft swiotlb=force' to simulate the worst
case. This is using v3.7-rc3.
The r8169 is booted without any arguments, the e1000e is using 'iommu=soft
swiotlb=force'.
So r8169 -> e1000e, I get ~940 (this is odd, I expected that the e1000e
on the recv side would be using the bounce buffer, but then I realized it
sets up using pci_alloc_coherent an 'dma' pool).
The other way - e1000e -> r8169 got me around ~128. So it is the sending
side that ends up using the bounce buffer and it slows down considerably.
I also swapped the machine that had e1000e with a tg3 - and got around
the same numbers.
So all of this points to the swiotlb and to just make sure that nothing
was amiss I wrote a little driver that would allocate a compound page,
setup DMA mapping, do some writes, sync and unmap the DMA page. And it works
correctly - so swiotlb (and the xen variant) work right just right.
Attached for your fun.
Then I decided to try v3.6.3, with the same exact parameters.. and
the problem went away.
The e1000e -> r8169 which got me around ~128, now gets ~940! Still
using the swiotlb bounce buffer.
>
> Because ssh use small packets, and small TCP packets dont use frags but
> skb->head.
>
> You mentioned a 70% drop of performance, but what test have you used
> exactly ?
Note, I did not provide any arguments to netperf, but it did pick the
test you wanted:
> netperf -H tst019
TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to tst019.dumpdata.com (192.168.101.39) port 0 AF_INET
>
>
[-- Attachment #2: dma_test.c --]
[-- Type: text/plain, Size: 5698 bytes --]
#include <linux/module.h>
#include <linux/kthread.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/dma-mapping.h>
#include <linux/slab.h>
#include <xen/page.h>
#define DMA_TEST "0.1"
MODULE_AUTHOR("Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>");
MODULE_DESCRIPTION("dma_test");
MODULE_LICENSE("GPL");
MODULE_VERSION(DMA_TEST);
static struct bus_type fallback_bus_type = {
.name = "fallback_bus:",
};
static void fake_release(struct device *dev)
{
/* No kfree as the device was allocated on stack. */
}
struct args {
int len;
enum dma_data_direction dir;
};
#define MAGIC_DEVICE 0xffffffdd
#define MAGIC_CPU 0xffffffcc
static int dma_test_thread(void *arg)
{
struct page *page;
dma_addr_t dma_addr = 0;
struct device fake = {
.coherent_dma_mask = DMA_BIT_MASK(32),
.bus = &fallback_bus_type,
.release = fake_release,
};
gfp_t gfp = __GFP_COMP | __GFP_NOWARN | GFP_ATOMIC;
int ret;
int i;
void *addr;
struct page *p;
struct args *args = (struct args *)arg;
int dir = args->dir;
int len = args->len;
dev_set_name(&fake, "%s", dir == DMA_TO_DEVICE ? "to_dev" : "to_cpu");
fake.dma_mask = &fake.coherent_dma_mask;
ret = device_register(&fake);
if (ret)
goto out;
do {
unsigned long prev_mfn = 0;
bool bus_and_dma_same;
page = alloc_pages(gfp, get_order(len));
p = page;
/* Check that the bus addresses are contingous. */
for (i = 0; i < len / PAGE_SIZE; i++, p++) {
unsigned long pfn, mfn;
addr = page_address(p);
pfn = PFN_DOWN(virt_to_phys(addr));
if (xen_domain())
mfn = pfn_to_mfn(pfn);
else
mfn = pfn;
if (i != 0) {
if (prev_mfn + 1 != mfn)
dev_warn(&fake, "va: %lx (pfn:%lx, mfn:%lx) w.r.t prev mfn: %lx!\n",
(unsigned long)addr, pfn, mfn, prev_mfn);
}
prev_mfn = mfn;
}
dma_addr = dma_map_page(&fake, page, 0 /* no offset */, len, dir);
/* Note, dma_addr is the physical address ! */
if (dma_mapping_error(&fake, dma_addr)) {
dev_warn(&fake, "DMA %lx for %lx is not right\n", (unsigned long)dma_addr,
(unsigned long)page_address(page));
__free_pages(page, get_order(len));
page = NULL;
}
bus_and_dma_same = false;
if (page) {
unsigned long phys;
unsigned long pfn, mfn, bus_addr_mfn;
unsigned long bus_addr = 0;
p = page;
for (i = 0; i < len / PAGE_SIZE; i++, p++) {
void *bus_va;
addr = page_address(p);
phys = virt_to_phys(addr);
pfn = PFN_DOWN(phys);
bus_va = (void *)(dma_addr + (i * PAGE_SIZE));
if (xen_domain()) {
void * tmp;
/* Find the bus frame for the physical frame*/
mfn = pfn_to_mfn(pfn);
/* and .. voodoo time! */
bus_addr_mfn = PFN_DOWN(dma_addr + (i * PAGE_SIZE));
bus_addr = PFN_PHYS(mfn_to_pfn(bus_addr_mfn));
tmp = __va(bus_addr);
bus_va = mfn_to_virt(bus_addr_mfn);
WARN(bus_va != tmp, "Expected %lx (%lx+%d*PAGE_SIZE), got: %lx (pfn: %lx, mfn: %lx)!\n",
(unsigned long)bus_va, (unsigned long)dma_addr, i, (unsigned long)tmp, PFN_DOWN(bus_addr), bus_addr_mfn);
} else {
mfn = pfn;
bus_addr = (unsigned long)bus_va;
/* Assume DMA addr == physical addr */
bus_addr_mfn = PFN_DOWN(bus_addr);
bus_va = __va(PFN_PHYS(bus_addr_mfn));
}
dev_info(&fake, "%lx (pfn:%lx, bus frame: %lx) %s %lx (addr: %lx, frame: %lx)\n",
(unsigned long)addr, pfn, mfn,
dir == DMA_TO_DEVICE ? "=>" : "<=",
(unsigned long)bus_va, bus_addr, bus_addr_mfn);
if (!virt_addr_valid(bus_va))
break;
if (!virt_addr_valid(addr))
break;
/* CPU */
memset(addr, 0xCC, PAGE_SIZE);
/* Device */
memset(bus_va, 0xDD, PAGE_SIZE);
if (addr == bus_va)
bus_and_dma_same = true;
}
}
set_current_state(TASK_INTERRUPTIBLE);
schedule_timeout_interruptible(5*HZ);
if (!page)
continue;
p = page;
for (i = 0; i < len / PAGE_SIZE; i++, p++) {
if (bus_and_dma_same)
continue;
addr = page_address(p);
if (((char *)addr)[0] != MAGIC_CPU)
dev_warn(&fake, "%lx with DMA (%lx) has %x (expected %lx)\n",
(unsigned long)addr, (unsigned long)(dma_addr + (i * PAGE_SIZE)),
((char *)addr)[0], (unsigned long)MAGIC_CPU);
}
/* sync the page */
dma_sync_single_for_cpu(&fake, dma_addr, len, dir);
p = page;
for (i = 0; i < len / PAGE_SIZE; i++, p++) {
unsigned long check_val = MAGIC_DEVICE;
addr = page_address(p);
if (dir == DMA_TO_DEVICE)
check_val = MAGIC_CPU;
if (dir == DMA_FROM_DEVICE)
check_val = MAGIC_DEVICE;
dev_info(&fake, "%lx with DMA (%lx) has %x (expected %lx)\n",
(unsigned long)addr, (unsigned long)(dma_addr + (i * PAGE_SIZE)),
((char *)addr)[0], check_val);
}
dma_unmap_page(&fake, dma_addr, len, dir);
dma_addr = 0;
__free_pages(page, get_order(len));
page = NULL;
} while (!kthread_should_stop());
if (dma_addr)
dma_unmap_page(&fake, dma_addr, len, dir);
if (page)
__free_pages(page, get_order(len));
put_device(&fake);
device_unregister(&fake);
out:
return 0;
}
static struct task_struct *t[2];
static struct args a[2];
static int __init dma_test_init(void)
{
int ret;
/* No point doing this without SWIOTLB */
if (!swiotlb_nr_tbl())
return -ENODEV;
ret = bus_register(&fallback_bus_type);
if (ret)
return ret;
a[0].dir = DMA_TO_DEVICE;
a[0].len = 32768;
t[0] = kthread_run(dma_test_thread, &a[0], "dma_test_dev");
a[1].len = 16384;
a[1].dir = DMA_FROM_DEVICE;
t[1] = kthread_run(dma_test_thread, &a[1], "dma_test_cpu");
return 0;
}
static void __exit dma_test_exit(void)
{
if (t[0])
kthread_stop(t[0]);
if (t[1])
kthread_stop(t[1]);
bus_unregister(&fallback_bus_type);
}
module_init(dma_test_init);
module_exit(dma_test_exit);
^ permalink raw reply
* Re: [PATCH v3 10/10] net/macb: add pinctrl consumer support
From: Joachim Eastwood @ 2012-10-30 17:37 UTC (permalink / raw)
To: Nicolas Ferre
Cc: netdev, davem, havard, bhutchings, linux-arm-kernel, plagnioj,
patrice.vilchez, linux-kernel
In-Reply-To: <3269426bdd44debc00d027651f8248db9d40f3dc.1351591858.git.nicolas.ferre@atmel.com>
On 30 October 2012 11:18, Nicolas Ferre <nicolas.ferre@atmel.com> wrote:
> From: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
>
> If no pinctrl available just report a warning as some architecture may not
> need to do anything.
>
> Signed-off-by: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
> [nicolas.ferre@atmel.com: adapt the error path]
> Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
> Cc: netdev@vger.kernel.org
> ---
> drivers/net/ethernet/cadence/macb.c | 13 +++++++++++++
> 1 file changed, 13 insertions(+)
>
> diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
> index 4d51877..eae3d74 100644
> --- a/drivers/net/ethernet/cadence/macb.c
> +++ b/drivers/net/ethernet/cadence/macb.c
> @@ -26,6 +26,9 @@
> #include <linux/of.h>
> #include <linux/of_device.h>
> #include <linux/of_net.h>
> +#include <linux/of_gpio.h>
> +#include <linux/gpio.h>
Why are these two headers added?
I don't see anything from them used in the code added.
Wouldn't the pinctrl header by itself be sufficient?
> +#include <linux/pinctrl/consumer.h>
>
> #include "macb.h"
>
> @@ -1472,6 +1475,7 @@ static int __init macb_probe(struct platform_device *pdev)
> struct phy_device *phydev;
> u32 config;
> int err = -ENXIO;
> + struct pinctrl *pinctrl;
>
> regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
> if (!regs) {
> @@ -1479,6 +1483,15 @@ static int __init macb_probe(struct platform_device *pdev)
> goto err_out;
> }
>
> + pinctrl = devm_pinctrl_get_select_default(&pdev->dev);
> + if (IS_ERR(pinctrl)) {
> + err = PTR_ERR(pinctrl);
> + if (err == -EPROBE_DEFER)
> + goto err_out;
> +
> + dev_warn(&pdev->dev, "No pinctrl provided\n");
> + }
> +
> err = -ENOMEM;
> dev = alloc_etherdev(sizeof(*bp));
> if (!dev)
> --
regards
Joachim Eastwood
^ permalink raw reply
* Re: [PATCH v3 00/10] net/macb: driver enhancement concerning GEM support, ring logic and cleanup
From: Joachim Eastwood @ 2012-10-30 17:31 UTC (permalink / raw)
To: Nicolas Ferre
Cc: netdev, davem, havard, bhutchings, linux-arm-kernel, plagnioj,
patrice.vilchez, linux-kernel
In-Reply-To: <cover.1351591858.git.nicolas.ferre@atmel.com>
On 30 October 2012 11:17, Nicolas Ferre <nicolas.ferre@atmel.com> wrote:
> This is an enhancement work that began several years ago. I try to catchup with
> some performance improvement that has been implemented then by Havard.
> The ring index logic and the TX error path modification are the biggest changes
> but some cleanup/debugging have been added along the way.
> The GEM revision will benefit from the Gigabit support.
> Newer pinctrl infrastructure support is added but it is optional.
>
> The series has been tested on several Atmel AT91 SoC with the two MACB/GEM
> flavors.
Gave the patch series a quick spin on RM9200 as well and the
at91_ether driver still works. Not many patches here that touch the
shared code though.
So FWIW;
Tested-by: Joachim Eastwood <manabian@gmail.com>
Note: Needed the patch you sent out (net/at91_ether: fix the use of
macb structure) to fix the build error on the struct rename.
regards
Joachim Eastwood
^ permalink raw reply
* Re: [PATCH] net: allow configuration of the size of page in __netdev_alloc_frag
From: Konrad Rzeszutek Wilk @ 2012-10-30 17:23 UTC (permalink / raw)
To: Eric Dumazet
Cc: netdev@vger.kernel.org, Eric Dumazet, Ian Campbell,
xen-devel@lists.xen.org
In-Reply-To: <20121030165309.GA30483@phenom.dumpdata.com>
On Tue, Oct 30, 2012 at 12:53:09PM -0400, Konrad Rzeszutek Wilk wrote:
> On Wed, Oct 24, 2012 at 06:43:20PM +0200, Eric Dumazet wrote:
> > On Wed, 2012-10-24 at 17:22 +0100, Ian Campbell wrote:
> > > On Wed, 2012-10-24 at 16:21 +0100, Eric Dumazet wrote:
> >
> > > > If you really have such problems, why locally generated TCP traffic
> > > > doesnt also have it ?
> > >
> > > I think it does. The reason I noticed the original problem was that ssh
> > > to the machine was virtually (no pun intended) unusable.
> > >
> > > > Your patch doesnt touch sk_page_frag_refill(), does it ?
> > >
> > > That's right. It doesn't. When is (sk->sk_allocation & __GFP_WAIT) true?
> > > Is it possible I'm just not hitting that case?
> > >
> >
> > I hope not. GFP_KERNEL has __GFP_WAIT.
> >
> > > Is it possible that this only affects certain traffic patterns (I only
> > > really tried ssh/scp and ping)? Or perhaps its just that the swiotlb is
> > > only broken in one corner case and not the other.
> >
> > Could you try a netperf -t TCP_STREAM ?
>
> For fun I did a couple of tests - I setup two machines (one r8168, the other
> e1000e) and tried to do netperf/netserver. Both of them are running a baremetal
> kernel and one of them has 'iommu=soft swiotlb=force' to simulate the worst
> case. This is using v3.7-rc3.
I also did a test with the patch at the top, with the same setup and ... it
does look like it fixes some issues, but not the underlaying one.
The same test, with net.core.netdev_frag_page_max_order=0, the e1000e->r8169
gets ~124, but then on subsequent runs it picks up to ~933. If I let the
machine stay a bit idle and then do this again, it does around ~124 again.
Thoughts?
^ permalink raw reply
* [PATCH] bonding: extend bond_arp_send_all to bridge devices
From: Chris J Arges @ 2012-10-30 17:07 UTC (permalink / raw)
To: netdev; +Cc: Andy Gospodarek
[-- Attachment #1: Type: text/plain, Size: 308 bytes --]
Hi, please accept this patch that fixes the following issues:
http://bugzilla.kernel.org/show_bug.cgi?id=31822
http://launchpad.net/bugs/736226
I've done a bit of testing with the setup identified in the bugs, and
this patch fixes the issue for me and others that have tested this.
Thanks,
--chris j arges
[-- Attachment #2: 0001-bonding-extend-bond_arp_send_all-to-bridge-devices.patch --]
[-- Type: text/x-patch, Size: 1701 bytes --]
>From bc58ecc70aecc68497fe54228ebe8630777b53a0 Mon Sep 17 00:00:00 2001
From: Chris J Arges <chris.j.arges@canonical.com>
Date: Thu, 6 Sep 2012 14:17:40 -0500
Subject: [PATCH] bonding: extend bond_arp_send_all to bridge devices
ARP monitoring does not work when we have a network in the
following configuration:
eth0----+ +----bond0.100----br0-100---{+virtual machines
| |
+----bond0----+----br0---(fixed IP)->--{LAN arp_ip_target}
| |
eth1----+ +----bond0.200----br0-200---{+virtual machines
This patch extends bond_arp_send_all to also check if a device
is also in a bridge.
This is related to the following issues:
http://launchpad.net/bugs/736226
http://bugzilla.kernel.org/show_bug.cgi?id=31822
Thanks to help from Andy Gospodarek.
Signed-off-by: Chris J Arges <chris.j.arges@canonical.com>
---
drivers/net/bonding/bond_main.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b2530b0..cb791f6 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2708,6 +2708,18 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
continue;
}
+ /*
+ * Check if the target is part of a bridge.
+ */
+ if (rt->dst.dev->priv_flags & IFF_EBRIDGE) {
+ /* Confirm addr is part of the bridge */
+ addr = bond_confirm_addr(rt->dst.dev, targets[i], 0);
+
+ /* Send ARP request */
+ bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], addr, 0);
+ continue;
+ }
+
if (net_ratelimit()) {
pr_warning("%s: no path to arp_ip_target %pI4 via rt.dev %s\n",
bond->dev->name, &targets[i],
--
1.7.10.4
^ permalink raw reply related
* Re: [PATCH v3 2/6] PM / Runtime: introduce pm_runtime_set[get]_memalloc_noio()
From: Alan Stern @ 2012-10-30 16:54 UTC (permalink / raw)
To: Ming Lei
Cc: linux-kernel, Oliver Neukum, Minchan Kim, Greg Kroah-Hartman,
Rafael J. Wysocki, Jens Axboe, David S. Miller, Andrew Morton,
netdev, linux-usb, linux-pm, linux-mm
In-Reply-To: <CACVXFVO5-UPNrWsySzDE5AfOv1TMqbyitQX9ViidSJPM36fqAQ@mail.gmail.com>
On Wed, 31 Oct 2012, Ming Lei wrote:
> On Tue, Oct 30, 2012 at 11:38 PM, Alan Stern <stern@rowland.harvard.edu> wrote:
>
> >
> > Okay, I see your point. But acquiring the lock here doesn't solve the
> > problem. Suppose a thread is about to reset a USB mass-storage device.
> > It acquires the lock and sees that the noio flag is clear. But before
> > it can issue the reset, another thread sets the noio flag.
>
> If the USB mass-storage device is being reseted, the flag should be set
> already generally. If the flag is still unset, that means the disk/network
> device isn't added into system(or removed just now), so memory allocation
> with block I/O should be allowed during the reset. Looks it isn't one problem,
> isn't it?
As Oliver said, it can be a problem.
> > Lastly, pm_runtime_get_memalloc_noio always returns false when
> > CONFIG_PM_RUNTIME is disabled. But we still need to prevent I/O during
> > usb_reset_device even when there's no runtime PM. Maybe the simplest
> > answer is always to set noio during resets. That would also help with
> > the race described above.
>
> I have thought about this. IMO, pm_runtime_get_memalloc_noio should
> return true always if CONFIG_PM_RUNTIME is unset.
That's okay as long as the only user of pm_runtime_get_memalloc_noio
(apart from the runtime PM core) is usbcore.
Alan Stern
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply
* Re: IPV6_PKTINFO seems not to be honored correctly by RAW-sockets
From: Steven Barth @ 2012-10-30 16:52 UTC (permalink / raw)
To: Eric Dumazet; +Cc: netdev
In-Reply-To: <1351593768.12280.779.camel@edumazet-glaptop>
Thanks for your quick reply.
I just saw that there is also a IPV6_PKTINFO setsockopt-option which was
probably what your patch affects.
However what I actually meant was the IPV6_PKTINFO control message for
sendmsg. Sorry for being ambiguous here. I tried to trace the bug down a
bit further with my unfortunately very limited kernel debugging skills.
It seems that the destined interface is correctly set in fl6->flowi6_oif
also still when it reaches ip6_push_pending_frames in ip6_output.c so I
guess it must be lost some time later but I couldn't find out exactly
where yet. I'll try to find more information later if I can find some
free time.
Regards,
Steven
On 30.10.2012 11:42, Eric Dumazet wrote:
> From: Eric Dumazet <edumazet@google.com>
>
> On Tue, 2012-10-30 at 09:58 +0100, Steven Barth wrote:
>> Hi,
>>
>> I recently noticed that there might be an unexpected behavior in the
>> handling of IPV6_PKTINFO for RAW-sockets. It seems that the given
>> destination interface is ignored.
>>
>> I just reproduced this on 3.7.0-rc3 vanilla but some quick tests with
>> 2.6.32 and 3.5 distro-kernels on different machines showed the same.
>>
>> I've noticed this first in my own software but I could also reproduce it
>> easily with standard tools like ping6 from iputils:
>>
>> Have 2 network interfaces with (global) IPv6-addresses assigned (e.g.
>> eth0 with fd00::1/64 and eth1 with fd01::1/64) and do a ping6 -I eth1
>> fd00::1 (ping6 from iputils uses IPV6_PKTINFO internally).
>>
>> For me the result was that even though I set the interface to eth1 the
>> ECHO was still send to eth0.
>>
>> Also (although probably unrelated) forwarding for IPv6 was disabled.
>>
>> If I try something similar with IPv4 and ping -I ... the ECHO doesn't go
>> out on eth0 but - as expected - on eth1.
>>
>> However if I use traceroute(6) with -I (ICMP-traceroute) and the -i
>> option to determine the interface, packages seem to be sent through the
>> expected interface. Internally it seems that traceroute(6) uses
>> SO_BINDTODEVICE instead of IP(V6)_PKTINFO which seems to work.
>>
>> So it seems there might be something wrong with IPV6_PKTINFO or is this
>> expected behavior?
>>
>
> I believe its not expected behavior.
>
> Is the following patch fixing it ?
>
> Thanks
>
> [PATCH] ipv6: raw: honor IPV6_PKTINFO
>
> Let ping6 -I interface works correctly.
>
> If socket was not bound to a given interface, check if IPV6_PKTINFO was
> issued on this socket.
>
> Reported-by: Steven Barth <steven@midlink.org>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> ---
> diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
> index d8e95c7..363ee65 100644
> --- a/net/ipv6/raw.c
> +++ b/net/ipv6/raw.c
> @@ -814,8 +814,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
> fl6.flowlabel = np->flow_label;
> }
>
> - if (fl6.flowi6_oif == 0)
> - fl6.flowi6_oif = sk->sk_bound_dev_if;
> + if (!fl6.flowi6_oif)
> + fl6.flowi6_oif = sk->sk_bound_dev_if ?: np->sticky_pktinfo.ipi6_ifindex;
>
> if (msg->msg_controllen) {
> opt = &opt_space;
>
>
^ permalink raw reply
* Re: [PATCH v3 2/6] PM / Runtime: introduce pm_runtime_set[get]_memalloc_noio()
From: Oliver Neukum @ 2012-10-30 16:30 UTC (permalink / raw)
To: Ming Lei
Cc: Alan Stern, linux-kernel, Minchan Kim, Greg Kroah-Hartman,
Rafael J. Wysocki, Jens Axboe, David S. Miller, Andrew Morton,
netdev, linux-usb, linux-pm, linux-mm
In-Reply-To: <CACVXFVO5-UPNrWsySzDE5AfOv1TMqbyitQX9ViidSJPM36fqAQ@mail.gmail.com>
On Wednesday 31 October 2012 00:00:56 Ming Lei wrote:
> On Tue, Oct 30, 2012 at 11:38 PM, Alan Stern <stern@rowland.harvard.edu> wrote:
>
> >
> > Okay, I see your point. But acquiring the lock here doesn't solve the
> > problem. Suppose a thread is about to reset a USB mass-storage device.
> > It acquires the lock and sees that the noio flag is clear. But before
> > it can issue the reset, another thread sets the noio flag.
>
> If the USB mass-storage device is being reseted, the flag should be set
> already generally. If the flag is still unset, that means the disk/network
> device isn't added into system(or removed just now), so memory allocation
> with block I/O should be allowed during the reset. Looks it isn't one problem,
> isn't it?
I am afraid it is, because a disk may just have been probed as the deviceis being reset.
Regards
Oliver
^ permalink raw reply
* Re: [PATCH v3 2/6] PM / Runtime: introduce pm_runtime_set[get]_memalloc_noio()
From: Ming Lei @ 2012-10-30 16:15 UTC (permalink / raw)
To: Alan Stern
Cc: linux-kernel, Oliver Neukum, Minchan Kim, Greg Kroah-Hartman,
Rafael J. Wysocki, Jens Axboe, David S. Miller, Andrew Morton,
netdev, linux-usb, linux-pm, linux-mm
In-Reply-To: <CACVXFVO5-UPNrWsySzDE5AfOv1TMqbyitQX9ViidSJPM36fqAQ@mail.gmail.com>
On Wed, Oct 31, 2012 at 12:00 AM, Ming Lei <ming.lei@canonical.com> wrote:
>
> Looks the simplest approach is to handle the noio flag thing at the start and
> end of rpm_resume.
Sorry, that doesn't work, runtime_suspend need that too because memory
allocation with block I/O might deadlock when doing I/O on the same device.
Thanks,
--
Ming Lei
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply
* Re: [PATCH v3 2/6] PM / Runtime: introduce pm_runtime_set[get]_memalloc_noio()
From: Ming Lei @ 2012-10-30 16:00 UTC (permalink / raw)
To: Alan Stern
Cc: linux-kernel, Oliver Neukum, Minchan Kim, Greg Kroah-Hartman,
Rafael J. Wysocki, Jens Axboe, David S. Miller, Andrew Morton,
netdev, linux-usb, linux-pm, linux-mm
In-Reply-To: <Pine.LNX.4.44L0.1210301112270.1363-100000@iolanthe.rowland.org>
On Tue, Oct 30, 2012 at 11:38 PM, Alan Stern <stern@rowland.harvard.edu> wrote:
>
> Okay, I see your point. But acquiring the lock here doesn't solve the
> problem. Suppose a thread is about to reset a USB mass-storage device.
> It acquires the lock and sees that the noio flag is clear. But before
> it can issue the reset, another thread sets the noio flag.
If the USB mass-storage device is being reseted, the flag should be set
already generally. If the flag is still unset, that means the disk/network
device isn't added into system(or removed just now), so memory allocation
with block I/O should be allowed during the reset. Looks it isn't one problem,
isn't it?
> I'm not sure what the best solution is.
>
>> The lock needn't to be held when the function is called inside
>> pm_runtime_set_memalloc_noio(), so the bitfield flag should
>> be checked directly without holding power lock in dev_memalloc_noio().
>
> Yes.
>
> A couple of other things... Runtime resume can be blocked by runtime
> suspend, if a resume is requested while the suspend is in progress.
> Therefore the runtime suspend code also needs to save-set-restore the
> noio flag.
Looks the simplest approach is to handle the noio flag thing at the start and
end of rpm_resume.
> Also, we should set the noio flag at the start of
> usb_stor_control_thread, because everything that thread does can
> potentially block an I/O operation.
Yes, it should be done, and all GFP_NOIO in usbcore should be converted
into GFP_KERNEL together. And the work shouldn't be started until
the patchset is merged.
> Lastly, pm_runtime_get_memalloc_noio always returns false when
> CONFIG_PM_RUNTIME is disabled. But we still need to prevent I/O during
> usb_reset_device even when there's no runtime PM. Maybe the simplest
> answer is always to set noio during resets. That would also help with
> the race described above.
I have thought about this. IMO, pm_runtime_get_memalloc_noio should
return true always if CONFIG_PM_RUNTIME is unset.
Thanks,
--
Ming Lei
^ permalink raw reply
* tcp_metrics: dumb bug
From: Stephen Hemminger @ 2012-10-30 15:59 UTC (permalink / raw)
To: Julian Anastasov; +Cc: netdev
https://bugzilla.kernel.org/show_bug.cgi?id=49171
Description From David Binderman 2012-10-21 10:31:05 (-) [reply]
The source code is
if (nla_len(a) != sizeof(sizeof(struct in6_addr)))
I'm surprised that compiles. Suggest remove one of the sizeofs.
^ permalink raw reply
* Re: [PATCH net-next 2/8] skb: api to report errors for zero copy skbs
From: Michael S. Tsirkin @ 2012-10-30 15:54 UTC (permalink / raw)
To: Vlad Yasevich
Cc: Alexander Duyck, Ian Campbell, kvm, netdev, linux-kernel,
virtualization, Eric Dumazet, Andrew Morton, David S. Miller
In-Reply-To: <508FF5D0.6080107@redhat.com>
On Tue, Oct 30, 2012 at 11:44:16AM -0400, Vlad Yasevich wrote:
> On 10/29/2012 11:49 AM, Michael S. Tsirkin wrote:
> >Orphaning frags for zero copy skbs needs to allocate data in atomic
> >context so is has a chance to fail. If it does we currently discard
> >the skb which is safe, but we don't report anything to the caller,
> >so it can not recover by e.g. disabling zero copy.
> >
> >Add an API to free skb reporting such errors: this is used
> >by tun in case orphaning frags fails.
> >
> >Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> >---
> > include/linux/skbuff.h | 1 +
> > net/core/skbuff.c | 19 +++++++++++++++++++
> > 2 files changed, 20 insertions(+)
> >
> >diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> >index 8bac11b..0644432 100644
> >--- a/include/linux/skbuff.h
> >+++ b/include/linux/skbuff.h
> >@@ -568,6 +568,7 @@ static inline struct rtable *skb_rtable(const struct sk_buff *skb)
> > }
> >
> > extern void kfree_skb(struct sk_buff *skb);
> >+extern void skb_tx_error(struct sk_buff *skb, int err);
> > extern void consume_skb(struct sk_buff *skb);
> > extern void __kfree_skb(struct sk_buff *skb);
> > extern struct kmem_cache *skbuff_head_cache;
> >diff --git a/net/core/skbuff.c b/net/core/skbuff.c
> >index eb31f6e..ad99c64 100644
> >--- a/net/core/skbuff.c
> >+++ b/net/core/skbuff.c
> >@@ -635,6 +635,25 @@ void kfree_skb(struct sk_buff *skb)
> > EXPORT_SYMBOL(kfree_skb);
> >
> > /**
> >+ * kfree_skb_on_error - report an sk_buff xmit error
> >+ * @skb: buffer that triggered an error
> >+ *
> >+ * Report xmit error if a device callback is tracking this skb.
> >+ */
>
> Nit: Comment doesn't match new function.
>
> -vlad
Good catch, thanks.
> >+void skb_tx_error(struct sk_buff *skb, int err)
> >+{
> >+ if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
> >+ struct ubuf_info *uarg;
> >+
> >+ uarg = skb_shinfo(skb)->destructor_arg;
> >+ if (uarg->callback)
> >+ uarg->callback(uarg, err);
> >+ skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY;
> >+ }
> >+}
> >+EXPORT_SYMBOL(skb_tx_error);
> >+
> >+/**
> > * consume_skb - free an skbuff
> > * @skb: buffer to free
> > *
> >
^ permalink raw reply
* Re: [PATCH net-next 8/8] vhost-net: reduce vq polling on tx zerocopy
From: Michael S. Tsirkin @ 2012-10-30 15:54 UTC (permalink / raw)
To: Vlad Yasevich
Cc: Alexander Duyck, Ian Campbell, kvm, netdev, linux-kernel,
virtualization, Eric Dumazet, Andrew Morton, David S. Miller
In-Reply-To: <508FF6A1.5060201@redhat.com>
On Tue, Oct 30, 2012 at 11:47:45AM -0400, Vlad Yasevich wrote:
> On 10/29/2012 11:49 AM, Michael S. Tsirkin wrote:
> >It seems that to avoid deadlocks it is enough to poll vq before
> > we are going to use the last buffer. This should be faster than
> >c70aa540c7a9f67add11ad3161096fb95233aa2e.
> >
> >Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> >---
> > drivers/vhost/net.c | 12 ++++++++++--
> > 1 file changed, 10 insertions(+), 2 deletions(-)
> >
> >diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> >index 8e9de79..3967f82 100644
> >--- a/drivers/vhost/net.c
> >+++ b/drivers/vhost/net.c
> >@@ -197,8 +197,16 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, int status)
> > {
> > struct vhost_ubuf_ref *ubufs = ubuf->ctx;
> > struct vhost_virtqueue *vq = ubufs->vq;
> >-
> >- vhost_poll_queue(&vq->poll);
> >+ int cnt = atomic_read(&ubufs->kref.refcount);
> >+
> >+ /*
> >+ * Trigger polling thread if guest stopped submitting new buffers:
> >+ * in this case, the refcount after decrement will eventually reach 1
> >+ * so here it is 2.
> >+ * We also trigger polling periodically after each 16 packets.
> >+ */
> >+ if (cnt <= 2 || !(cnt % 16))
>
> Why 16? Does it make sense to make it configurable?
>
> -vlad
Probably not but I'll add a comment explaining why.
> >+ vhost_poll_queue(&vq->poll);
> > /* set len to mark this desc buffers done DMA */
> > vq->heads[ubuf->desc].len = status ?
> > VHOST_DMA_FAILED_LEN : VHOST_DMA_DONE_LEN;
> >
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox