mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 09:19:51 +00:00
![Tejun Heo](/assets/img/avatar_default.png)
percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
502 lines
14 KiB
C
502 lines
14 KiB
C
/*
|
|
* Copyright (c) 2006 Oracle. All rights reserved.
|
|
*
|
|
* This software is available to you under a choice of one of two
|
|
* licenses. You may choose to be licensed under the terms of the GNU
|
|
* General Public License (GPL) Version 2, available from the file
|
|
* COPYING in the main directory of this source tree, or the
|
|
* OpenIB.org BSD license below:
|
|
*
|
|
* Redistribution and use in source and binary forms, with or
|
|
* without modification, are permitted provided that the following
|
|
* conditions are met:
|
|
*
|
|
* - Redistributions of source code must retain the above
|
|
* copyright notice, this list of conditions and the following
|
|
* disclaimer.
|
|
*
|
|
* - Redistributions in binary form must reproduce the above
|
|
* copyright notice, this list of conditions and the following
|
|
* disclaimer in the documentation and/or other materials
|
|
* provided with the distribution.
|
|
*
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
|
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
|
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
|
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
|
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
|
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
|
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
* SOFTWARE.
|
|
*
|
|
*/
|
|
#include <linux/kernel.h>
|
|
#include <linux/list.h>
|
|
#include <linux/slab.h>
|
|
#include <net/inet_hashtables.h>
|
|
|
|
#include "rds.h"
|
|
#include "loop.h"
|
|
#include "rdma.h"
|
|
|
|
#define RDS_CONNECTION_HASH_BITS 12
|
|
#define RDS_CONNECTION_HASH_ENTRIES (1 << RDS_CONNECTION_HASH_BITS)
|
|
#define RDS_CONNECTION_HASH_MASK (RDS_CONNECTION_HASH_ENTRIES - 1)
|
|
|
|
/* converting this to RCU is a chore for another day.. */
|
|
static DEFINE_SPINLOCK(rds_conn_lock);
|
|
static unsigned long rds_conn_count;
|
|
static struct hlist_head rds_conn_hash[RDS_CONNECTION_HASH_ENTRIES];
|
|
static struct kmem_cache *rds_conn_slab;
|
|
|
|
static struct hlist_head *rds_conn_bucket(__be32 laddr, __be32 faddr)
|
|
{
|
|
/* Pass NULL, don't need struct net for hash */
|
|
unsigned long hash = inet_ehashfn(NULL,
|
|
be32_to_cpu(laddr), 0,
|
|
be32_to_cpu(faddr), 0);
|
|
return &rds_conn_hash[hash & RDS_CONNECTION_HASH_MASK];
|
|
}
|
|
|
|
#define rds_conn_info_set(var, test, suffix) do { \
|
|
if (test) \
|
|
var |= RDS_INFO_CONNECTION_FLAG_##suffix; \
|
|
} while (0)
|
|
|
|
static inline int rds_conn_is_sending(struct rds_connection *conn)
|
|
{
|
|
int ret = 0;
|
|
|
|
if (!mutex_trylock(&conn->c_send_lock))
|
|
ret = 1;
|
|
else
|
|
mutex_unlock(&conn->c_send_lock);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static struct rds_connection *rds_conn_lookup(struct hlist_head *head,
|
|
__be32 laddr, __be32 faddr,
|
|
struct rds_transport *trans)
|
|
{
|
|
struct rds_connection *conn, *ret = NULL;
|
|
struct hlist_node *pos;
|
|
|
|
hlist_for_each_entry(conn, pos, head, c_hash_node) {
|
|
if (conn->c_faddr == faddr && conn->c_laddr == laddr &&
|
|
conn->c_trans == trans) {
|
|
ret = conn;
|
|
break;
|
|
}
|
|
}
|
|
rdsdebug("returning conn %p for %pI4 -> %pI4\n", ret,
|
|
&laddr, &faddr);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* This is called by transports as they're bringing down a connection.
|
|
* It clears partial message state so that the transport can start sending
|
|
* and receiving over this connection again in the future. It is up to
|
|
* the transport to have serialized this call with its send and recv.
|
|
*/
|
|
void rds_conn_reset(struct rds_connection *conn)
|
|
{
|
|
rdsdebug("connection %pI4 to %pI4 reset\n",
|
|
&conn->c_laddr, &conn->c_faddr);
|
|
|
|
rds_stats_inc(s_conn_reset);
|
|
rds_send_reset(conn);
|
|
conn->c_flags = 0;
|
|
|
|
/* Do not clear next_rx_seq here, else we cannot distinguish
|
|
* retransmitted packets from new packets, and will hand all
|
|
* of them to the application. That is not consistent with the
|
|
* reliability guarantees of RDS. */
|
|
}
|
|
|
|
/*
|
|
* There is only every one 'conn' for a given pair of addresses in the
|
|
* system at a time. They contain messages to be retransmitted and so
|
|
* span the lifetime of the actual underlying transport connections.
|
|
*
|
|
* For now they are not garbage collected once they're created. They
|
|
* are torn down as the module is removed, if ever.
|
|
*/
|
|
static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr,
|
|
struct rds_transport *trans, gfp_t gfp,
|
|
int is_outgoing)
|
|
{
|
|
struct rds_connection *conn, *parent = NULL;
|
|
struct hlist_head *head = rds_conn_bucket(laddr, faddr);
|
|
unsigned long flags;
|
|
int ret;
|
|
|
|
spin_lock_irqsave(&rds_conn_lock, flags);
|
|
conn = rds_conn_lookup(head, laddr, faddr, trans);
|
|
if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport &&
|
|
!is_outgoing) {
|
|
/* This is a looped back IB connection, and we're
|
|
* called by the code handling the incoming connect.
|
|
* We need a second connection object into which we
|
|
* can stick the other QP. */
|
|
parent = conn;
|
|
conn = parent->c_passive;
|
|
}
|
|
spin_unlock_irqrestore(&rds_conn_lock, flags);
|
|
if (conn)
|
|
goto out;
|
|
|
|
conn = kmem_cache_zalloc(rds_conn_slab, gfp);
|
|
if (conn == NULL) {
|
|
conn = ERR_PTR(-ENOMEM);
|
|
goto out;
|
|
}
|
|
|
|
INIT_HLIST_NODE(&conn->c_hash_node);
|
|
conn->c_laddr = laddr;
|
|
conn->c_faddr = faddr;
|
|
spin_lock_init(&conn->c_lock);
|
|
conn->c_next_tx_seq = 1;
|
|
|
|
mutex_init(&conn->c_send_lock);
|
|
INIT_LIST_HEAD(&conn->c_send_queue);
|
|
INIT_LIST_HEAD(&conn->c_retrans);
|
|
|
|
ret = rds_cong_get_maps(conn);
|
|
if (ret) {
|
|
kmem_cache_free(rds_conn_slab, conn);
|
|
conn = ERR_PTR(ret);
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* This is where a connection becomes loopback. If *any* RDS sockets
|
|
* can bind to the destination address then we'd rather the messages
|
|
* flow through loopback rather than either transport.
|
|
*/
|
|
if (rds_trans_get_preferred(faddr)) {
|
|
conn->c_loopback = 1;
|
|
if (is_outgoing && trans->t_prefer_loopback) {
|
|
/* "outgoing" connection - and the transport
|
|
* says it wants the connection handled by the
|
|
* loopback transport. This is what TCP does.
|
|
*/
|
|
trans = &rds_loop_transport;
|
|
}
|
|
}
|
|
|
|
conn->c_trans = trans;
|
|
|
|
ret = trans->conn_alloc(conn, gfp);
|
|
if (ret) {
|
|
kmem_cache_free(rds_conn_slab, conn);
|
|
conn = ERR_PTR(ret);
|
|
goto out;
|
|
}
|
|
|
|
atomic_set(&conn->c_state, RDS_CONN_DOWN);
|
|
conn->c_reconnect_jiffies = 0;
|
|
INIT_DELAYED_WORK(&conn->c_send_w, rds_send_worker);
|
|
INIT_DELAYED_WORK(&conn->c_recv_w, rds_recv_worker);
|
|
INIT_DELAYED_WORK(&conn->c_conn_w, rds_connect_worker);
|
|
INIT_WORK(&conn->c_down_w, rds_shutdown_worker);
|
|
mutex_init(&conn->c_cm_lock);
|
|
conn->c_flags = 0;
|
|
|
|
rdsdebug("allocated conn %p for %pI4 -> %pI4 over %s %s\n",
|
|
conn, &laddr, &faddr,
|
|
trans->t_name ? trans->t_name : "[unknown]",
|
|
is_outgoing ? "(outgoing)" : "");
|
|
|
|
/*
|
|
* Since we ran without holding the conn lock, someone could
|
|
* have created the same conn (either normal or passive) in the
|
|
* interim. We check while holding the lock. If we won, we complete
|
|
* init and return our conn. If we lost, we rollback and return the
|
|
* other one.
|
|
*/
|
|
spin_lock_irqsave(&rds_conn_lock, flags);
|
|
if (parent) {
|
|
/* Creating passive conn */
|
|
if (parent->c_passive) {
|
|
trans->conn_free(conn->c_transport_data);
|
|
kmem_cache_free(rds_conn_slab, conn);
|
|
conn = parent->c_passive;
|
|
} else {
|
|
parent->c_passive = conn;
|
|
rds_cong_add_conn(conn);
|
|
rds_conn_count++;
|
|
}
|
|
} else {
|
|
/* Creating normal conn */
|
|
struct rds_connection *found;
|
|
|
|
found = rds_conn_lookup(head, laddr, faddr, trans);
|
|
if (found) {
|
|
trans->conn_free(conn->c_transport_data);
|
|
kmem_cache_free(rds_conn_slab, conn);
|
|
conn = found;
|
|
} else {
|
|
hlist_add_head(&conn->c_hash_node, head);
|
|
rds_cong_add_conn(conn);
|
|
rds_conn_count++;
|
|
}
|
|
}
|
|
spin_unlock_irqrestore(&rds_conn_lock, flags);
|
|
|
|
out:
|
|
return conn;
|
|
}
|
|
|
|
struct rds_connection *rds_conn_create(__be32 laddr, __be32 faddr,
|
|
struct rds_transport *trans, gfp_t gfp)
|
|
{
|
|
return __rds_conn_create(laddr, faddr, trans, gfp, 0);
|
|
}
|
|
EXPORT_SYMBOL_GPL(rds_conn_create);
|
|
|
|
struct rds_connection *rds_conn_create_outgoing(__be32 laddr, __be32 faddr,
|
|
struct rds_transport *trans, gfp_t gfp)
|
|
{
|
|
return __rds_conn_create(laddr, faddr, trans, gfp, 1);
|
|
}
|
|
EXPORT_SYMBOL_GPL(rds_conn_create_outgoing);
|
|
|
|
void rds_conn_destroy(struct rds_connection *conn)
|
|
{
|
|
struct rds_message *rm, *rtmp;
|
|
|
|
rdsdebug("freeing conn %p for %pI4 -> "
|
|
"%pI4\n", conn, &conn->c_laddr,
|
|
&conn->c_faddr);
|
|
|
|
hlist_del_init(&conn->c_hash_node);
|
|
|
|
/* wait for the rds thread to shut it down */
|
|
atomic_set(&conn->c_state, RDS_CONN_ERROR);
|
|
cancel_delayed_work(&conn->c_conn_w);
|
|
queue_work(rds_wq, &conn->c_down_w);
|
|
flush_workqueue(rds_wq);
|
|
|
|
/* tear down queued messages */
|
|
list_for_each_entry_safe(rm, rtmp,
|
|
&conn->c_send_queue,
|
|
m_conn_item) {
|
|
list_del_init(&rm->m_conn_item);
|
|
BUG_ON(!list_empty(&rm->m_sock_item));
|
|
rds_message_put(rm);
|
|
}
|
|
if (conn->c_xmit_rm)
|
|
rds_message_put(conn->c_xmit_rm);
|
|
|
|
conn->c_trans->conn_free(conn->c_transport_data);
|
|
|
|
/*
|
|
* The congestion maps aren't freed up here. They're
|
|
* freed by rds_cong_exit() after all the connections
|
|
* have been freed.
|
|
*/
|
|
rds_cong_remove_conn(conn);
|
|
|
|
BUG_ON(!list_empty(&conn->c_retrans));
|
|
kmem_cache_free(rds_conn_slab, conn);
|
|
|
|
rds_conn_count--;
|
|
}
|
|
EXPORT_SYMBOL_GPL(rds_conn_destroy);
|
|
|
|
static void rds_conn_message_info(struct socket *sock, unsigned int len,
|
|
struct rds_info_iterator *iter,
|
|
struct rds_info_lengths *lens,
|
|
int want_send)
|
|
{
|
|
struct hlist_head *head;
|
|
struct hlist_node *pos;
|
|
struct list_head *list;
|
|
struct rds_connection *conn;
|
|
struct rds_message *rm;
|
|
unsigned long flags;
|
|
unsigned int total = 0;
|
|
size_t i;
|
|
|
|
len /= sizeof(struct rds_info_message);
|
|
|
|
spin_lock_irqsave(&rds_conn_lock, flags);
|
|
|
|
for (i = 0, head = rds_conn_hash; i < ARRAY_SIZE(rds_conn_hash);
|
|
i++, head++) {
|
|
hlist_for_each_entry(conn, pos, head, c_hash_node) {
|
|
if (want_send)
|
|
list = &conn->c_send_queue;
|
|
else
|
|
list = &conn->c_retrans;
|
|
|
|
spin_lock(&conn->c_lock);
|
|
|
|
/* XXX too lazy to maintain counts.. */
|
|
list_for_each_entry(rm, list, m_conn_item) {
|
|
total++;
|
|
if (total <= len)
|
|
rds_inc_info_copy(&rm->m_inc, iter,
|
|
conn->c_laddr,
|
|
conn->c_faddr, 0);
|
|
}
|
|
|
|
spin_unlock(&conn->c_lock);
|
|
}
|
|
}
|
|
|
|
spin_unlock_irqrestore(&rds_conn_lock, flags);
|
|
|
|
lens->nr = total;
|
|
lens->each = sizeof(struct rds_info_message);
|
|
}
|
|
|
|
static void rds_conn_message_info_send(struct socket *sock, unsigned int len,
|
|
struct rds_info_iterator *iter,
|
|
struct rds_info_lengths *lens)
|
|
{
|
|
rds_conn_message_info(sock, len, iter, lens, 1);
|
|
}
|
|
|
|
static void rds_conn_message_info_retrans(struct socket *sock,
|
|
unsigned int len,
|
|
struct rds_info_iterator *iter,
|
|
struct rds_info_lengths *lens)
|
|
{
|
|
rds_conn_message_info(sock, len, iter, lens, 0);
|
|
}
|
|
|
|
void rds_for_each_conn_info(struct socket *sock, unsigned int len,
|
|
struct rds_info_iterator *iter,
|
|
struct rds_info_lengths *lens,
|
|
int (*visitor)(struct rds_connection *, void *),
|
|
size_t item_len)
|
|
{
|
|
uint64_t buffer[(item_len + 7) / 8];
|
|
struct hlist_head *head;
|
|
struct hlist_node *pos;
|
|
struct hlist_node *tmp;
|
|
struct rds_connection *conn;
|
|
unsigned long flags;
|
|
size_t i;
|
|
|
|
spin_lock_irqsave(&rds_conn_lock, flags);
|
|
|
|
lens->nr = 0;
|
|
lens->each = item_len;
|
|
|
|
for (i = 0, head = rds_conn_hash; i < ARRAY_SIZE(rds_conn_hash);
|
|
i++, head++) {
|
|
hlist_for_each_entry_safe(conn, pos, tmp, head, c_hash_node) {
|
|
|
|
/* XXX no c_lock usage.. */
|
|
if (!visitor(conn, buffer))
|
|
continue;
|
|
|
|
/* We copy as much as we can fit in the buffer,
|
|
* but we count all items so that the caller
|
|
* can resize the buffer. */
|
|
if (len >= item_len) {
|
|
rds_info_copy(iter, buffer, item_len);
|
|
len -= item_len;
|
|
}
|
|
lens->nr++;
|
|
}
|
|
}
|
|
|
|
spin_unlock_irqrestore(&rds_conn_lock, flags);
|
|
}
|
|
EXPORT_SYMBOL_GPL(rds_for_each_conn_info);
|
|
|
|
static int rds_conn_info_visitor(struct rds_connection *conn,
|
|
void *buffer)
|
|
{
|
|
struct rds_info_connection *cinfo = buffer;
|
|
|
|
cinfo->next_tx_seq = conn->c_next_tx_seq;
|
|
cinfo->next_rx_seq = conn->c_next_rx_seq;
|
|
cinfo->laddr = conn->c_laddr;
|
|
cinfo->faddr = conn->c_faddr;
|
|
strncpy(cinfo->transport, conn->c_trans->t_name,
|
|
sizeof(cinfo->transport));
|
|
cinfo->flags = 0;
|
|
|
|
rds_conn_info_set(cinfo->flags,
|
|
rds_conn_is_sending(conn), SENDING);
|
|
/* XXX Future: return the state rather than these funky bits */
|
|
rds_conn_info_set(cinfo->flags,
|
|
atomic_read(&conn->c_state) == RDS_CONN_CONNECTING,
|
|
CONNECTING);
|
|
rds_conn_info_set(cinfo->flags,
|
|
atomic_read(&conn->c_state) == RDS_CONN_UP,
|
|
CONNECTED);
|
|
return 1;
|
|
}
|
|
|
|
static void rds_conn_info(struct socket *sock, unsigned int len,
|
|
struct rds_info_iterator *iter,
|
|
struct rds_info_lengths *lens)
|
|
{
|
|
rds_for_each_conn_info(sock, len, iter, lens,
|
|
rds_conn_info_visitor,
|
|
sizeof(struct rds_info_connection));
|
|
}
|
|
|
|
int __init rds_conn_init(void)
|
|
{
|
|
rds_conn_slab = kmem_cache_create("rds_connection",
|
|
sizeof(struct rds_connection),
|
|
0, 0, NULL);
|
|
if (rds_conn_slab == NULL)
|
|
return -ENOMEM;
|
|
|
|
rds_info_register_func(RDS_INFO_CONNECTIONS, rds_conn_info);
|
|
rds_info_register_func(RDS_INFO_SEND_MESSAGES,
|
|
rds_conn_message_info_send);
|
|
rds_info_register_func(RDS_INFO_RETRANS_MESSAGES,
|
|
rds_conn_message_info_retrans);
|
|
|
|
return 0;
|
|
}
|
|
|
|
void rds_conn_exit(void)
|
|
{
|
|
rds_loop_exit();
|
|
|
|
WARN_ON(!hlist_empty(rds_conn_hash));
|
|
|
|
kmem_cache_destroy(rds_conn_slab);
|
|
|
|
rds_info_deregister_func(RDS_INFO_CONNECTIONS, rds_conn_info);
|
|
rds_info_deregister_func(RDS_INFO_SEND_MESSAGES,
|
|
rds_conn_message_info_send);
|
|
rds_info_deregister_func(RDS_INFO_RETRANS_MESSAGES,
|
|
rds_conn_message_info_retrans);
|
|
}
|
|
|
|
/*
|
|
* Force a disconnect
|
|
*/
|
|
void rds_conn_drop(struct rds_connection *conn)
|
|
{
|
|
atomic_set(&conn->c_state, RDS_CONN_ERROR);
|
|
queue_work(rds_wq, &conn->c_down_w);
|
|
}
|
|
EXPORT_SYMBOL_GPL(rds_conn_drop);
|
|
|
|
/*
|
|
* An error occurred on the connection
|
|
*/
|
|
void
|
|
__rds_conn_error(struct rds_connection *conn, const char *fmt, ...)
|
|
{
|
|
va_list ap;
|
|
|
|
va_start(ap, fmt);
|
|
vprintk(fmt, ap);
|
|
va_end(ap);
|
|
|
|
rds_conn_drop(conn);
|
|
}
|