linux_dsm_epyc7002/net/core/sock.c

2976 lines
73 KiB
C
Raw Normal View History

/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Generic socket support routines. Memory allocators, socket lock/release
* handler for protocols to use and generic option handler.
*
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Florian La Roche, <flla@stud.uni-sb.de>
* Alan Cox, <A.Cox@swansea.ac.uk>
*
* Fixes:
* Alan Cox : Numerous verify_area() problems
* Alan Cox : Connecting on a connecting socket
* now returns an error for tcp.
* Alan Cox : sock->protocol is set correctly.
* and is not sometimes left as 0.
* Alan Cox : connect handles icmp errors on a
* connect properly. Unfortunately there
* is a restart syscall nasty there. I
* can't match BSD without hacking the C
* library. Ideas urgently sought!
* Alan Cox : Disallow bind() to addresses that are
* not ours - especially broadcast ones!!
* Alan Cox : Socket 1024 _IS_ ok for users. (fencepost)
* Alan Cox : sock_wfree/sock_rfree don't destroy sockets,
* instead they leave that for the DESTROY timer.
* Alan Cox : Clean up error flag in accept
* Alan Cox : TCP ack handling is buggy, the DESTROY timer
* was buggy. Put a remove_sock() in the handler
* for memory when we hit 0. Also altered the timer
* code. The ACK stuff can wait and needs major
* TCP layer surgery.
* Alan Cox : Fixed TCP ack bug, removed remove sock
* and fixed timer/inet_bh race.
* Alan Cox : Added zapped flag for TCP
* Alan Cox : Move kfree_skb into skbuff.c and tidied up surplus code
* Alan Cox : for new sk_buff allocations wmalloc/rmalloc now call alloc_skb
* Alan Cox : kfree_s calls now are kfree_skbmem so we can track skb resources
* Alan Cox : Supports socket option broadcast now as does udp. Packet and raw need fixing.
* Alan Cox : Added RCVBUF,SNDBUF size setting. It suddenly occurred to me how easy it was so...
* Rick Sladkey : Relaxed UDP rules for matching packets.
* C.E.Hawkins : IFF_PROMISC/SIOCGHWADDR support
* Pauline Middelink : identd support
* Alan Cox : Fixed connect() taking signals I think.
* Alan Cox : SO_LINGER supported
* Alan Cox : Error reporting fixes
* Anonymous : inet_create tidied up (sk->reuse setting)
* Alan Cox : inet sockets don't set sk->type!
* Alan Cox : Split socket option code
* Alan Cox : Callbacks
* Alan Cox : Nagle flag for Charles & Johannes stuff
* Alex : Removed restriction on inet fioctl
* Alan Cox : Splitting INET from NET core
* Alan Cox : Fixed bogus SO_TYPE handling in getsockopt()
* Adam Caldwell : Missing return in SO_DONTROUTE/SO_DEBUG code
* Alan Cox : Split IP from generic code
* Alan Cox : New kfree_skbmem()
* Alan Cox : Make SO_DEBUG superuser only.
* Alan Cox : Allow anyone to clear SO_DEBUG
* (compatibility fix)
* Alan Cox : Added optimistic memory grabbing for AF_UNIX throughput.
* Alan Cox : Allocator for a socket is settable.
* Alan Cox : SO_ERROR includes soft errors.
* Alan Cox : Allow NULL arguments on some SO_ opts
* Alan Cox : Generic socket allocation to make hooks
* easier (suggested by Craig Metz).
* Michael Pall : SO_ERROR returns positive errno again
* Steve Whitehouse: Added default destructor to free
* protocol private data.
* Steve Whitehouse: Added various other default routines
* common to several socket families.
* Chris Evans : Call suser() check last on F_SETOWN
* Jay Schulist : Added SO_ATTACH_FILTER and SO_DETACH_FILTER.
* Andi Kleen : Add sock_kmalloc()/sock_kfree_s()
* Andi Kleen : Fix write_space callback
* Chris Evans : Security fixes - signedness again
* Arnaldo C. Melo : cleanups, use skb_queue_purge
*
* To Fix:
*
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/errqueue.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/poll.h>
#include <linux/tcp.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/user_namespace.h>
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 14:31:31 +07:00
#include <linux/static_key.h>
#include <linux/memcontrol.h>
#include <linux/prefetch.h>
#include <asm/uaccess.h>
#include <linux/netdevice.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/net_namespace.h>
#include <net/request_sock.h>
#include <net/sock.h>
#include <linux/net_tstamp.h>
#include <net/xfrm.h>
#include <linux/ipsec.h>
cls_cgroup: Store classid in struct sock Up until now cls_cgroup has relied on fetching the classid out of the current executing thread. This runs into trouble when a packet processing is delayed in which case it may execute out of another thread's context. Furthermore, even when a packet is not delayed we may fail to classify it if soft IRQs have been disabled, because this scenario is indistinguishable from one where a packet unrelated to the current thread is processed by a real soft IRQ. In fact, the current semantics is inherently broken, as a single skb may be constructed out of the writes of two different tasks. A different manifestation of this problem is when the TCP stack transmits in response of an incoming ACK. This is currently unclassified. As we already have a concept of packet ownership for accounting purposes in the skb->sk pointer, this is a natural place to store the classid in a persistent manner. This patch adds the cls_cgroup classid in struct sock, filling up an existing hole on 64-bit :) The value is set at socket creation time. So all sockets created via socket(2) automatically gains the ID of the thread creating it. Whenever another process touches the socket by either reading or writing to it, we will change the socket classid to that of the process if it has a valid (non-zero) classid. For sockets created on inbound connections through accept(2), we inherit the classid of the original listening socket through sk_clone, possibly preceding the actual accept(2) call. In order to minimise risks, I have not made this the authoritative classid. For now it is only used as a backup when we execute with soft IRQs disabled. Once we're completely happy with its semantics we can use it as the sole classid. Footnote: I have rearranged the error path on cls_group module creation. If we didn't do this, then there is a window where someone could create a tc rule using cls_group before the cgroup subsystem has been registered. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-24 14:12:34 +07:00
#include <net/cls_cgroup.h>
#include <net/netprio_cgroup.h>
#include <linux/sock_diag.h>
#include <linux/filter.h>
#include <trace/events/sock.h>
#ifdef CONFIG_INET
#include <net/tcp.h>
#endif
#include <net/busy_poll.h>
static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
/**
* sk_ns_capable - General socket capability test
* @sk: Socket to use a capability on or through
* @user_ns: The user namespace of the capability to use
* @cap: The capability to use
*
* Test to see if the opener of the socket had when the socket was
* created and the current process has the capability @cap in the user
* namespace @user_ns.
*/
bool sk_ns_capable(const struct sock *sk,
struct user_namespace *user_ns, int cap)
{
return file_ns_capable(sk->sk_socket->file, user_ns, cap) &&
ns_capable(user_ns, cap);
}
EXPORT_SYMBOL(sk_ns_capable);
/**
* sk_capable - Socket global capability test
* @sk: Socket to use a capability on or through
* @cap: The global capability to use
*
* Test to see if the opener of the socket had when the socket was
* created and the current process has the capability @cap in all user
* namespaces.
*/
bool sk_capable(const struct sock *sk, int cap)
{
return sk_ns_capable(sk, &init_user_ns, cap);
}
EXPORT_SYMBOL(sk_capable);
/**
* sk_net_capable - Network namespace socket capability test
* @sk: Socket to use a capability on or through
* @cap: The capability to use
*
* Test to see if the opener of the socket had when the socket was created
* and the current process has the capability @cap over the network namespace
* the socket is a member of.
*/
bool sk_net_capable(const struct sock *sk, int cap)
{
return sk_ns_capable(sk, sock_net(sk)->user_ns, cap);
}
EXPORT_SYMBOL(sk_net_capable);
#ifdef CONFIG_MEMCG_KMEM
int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
{
struct proto *proto;
int ret = 0;
mutex_lock(&proto_list_mutex);
list_for_each_entry(proto, &proto_list, node) {
if (proto->init_cgroup) {
ret = proto->init_cgroup(memcg, ss);
if (ret)
goto out;
}
}
mutex_unlock(&proto_list_mutex);
return ret;
out:
list_for_each_entry_continue_reverse(proto, &proto_list, node)
if (proto->destroy_cgroup)
proto->destroy_cgroup(memcg);
mutex_unlock(&proto_list_mutex);
return ret;
}
void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg)
{
struct proto *proto;
mutex_lock(&proto_list_mutex);
list_for_each_entry_reverse(proto, &proto_list, node)
if (proto->destroy_cgroup)
proto->destroy_cgroup(memcg);
mutex_unlock(&proto_list_mutex);
}
#endif
/*
* Each address family might have different locking rules, so we have
* one slock key per address family:
*/
static struct lock_class_key af_family_keys[AF_MAX];
static struct lock_class_key af_family_slock_keys[AF_MAX];
#if defined(CONFIG_MEMCG_KMEM)
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 14:31:31 +07:00
struct static_key memcg_socket_limit_enabled;
EXPORT_SYMBOL(memcg_socket_limit_enabled);
#endif
/*
* Make lock validator output more readable. (we pre-construct these
* strings build-time, so that runtime initialization of socket
* locks is fast):
*/
static const char *const af_family_key_strings[AF_MAX+1] = {
"sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX" , "sk_lock-AF_INET" ,
"sk_lock-AF_AX25" , "sk_lock-AF_IPX" , "sk_lock-AF_APPLETALK",
"sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE" , "sk_lock-AF_ATMPVC" ,
"sk_lock-AF_X25" , "sk_lock-AF_INET6" , "sk_lock-AF_ROSE" ,
"sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI" , "sk_lock-AF_SECURITY" ,
"sk_lock-AF_KEY" , "sk_lock-AF_NETLINK" , "sk_lock-AF_PACKET" ,
"sk_lock-AF_ASH" , "sk_lock-AF_ECONET" , "sk_lock-AF_ATMSVC" ,
"sk_lock-AF_RDS" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" ,
"sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE" , "sk_lock-AF_LLC" ,
"sk_lock-27" , "sk_lock-28" , "sk_lock-AF_CAN" ,
"sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" ,
"sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" ,
"sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" ,
"sk_lock-AF_NFC" , "sk_lock-AF_VSOCK" , "sk_lock-AF_MAX"
};
static const char *const af_family_slock_key_strings[AF_MAX+1] = {
"slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" ,
"slock-AF_AX25" , "slock-AF_IPX" , "slock-AF_APPLETALK",
"slock-AF_NETROM", "slock-AF_BRIDGE" , "slock-AF_ATMPVC" ,
"slock-AF_X25" , "slock-AF_INET6" , "slock-AF_ROSE" ,
"slock-AF_DECnet", "slock-AF_NETBEUI" , "slock-AF_SECURITY" ,
"slock-AF_KEY" , "slock-AF_NETLINK" , "slock-AF_PACKET" ,
"slock-AF_ASH" , "slock-AF_ECONET" , "slock-AF_ATMSVC" ,
"slock-AF_RDS" , "slock-AF_SNA" , "slock-AF_IRDA" ,
"slock-AF_PPPOX" , "slock-AF_WANPIPE" , "slock-AF_LLC" ,
"slock-27" , "slock-28" , "slock-AF_CAN" ,
"slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" ,
"slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" ,
"slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" ,
"slock-AF_NFC" , "slock-AF_VSOCK" ,"slock-AF_MAX"
};
static const char *const af_family_clock_key_strings[AF_MAX+1] = {
"clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" ,
"clock-AF_AX25" , "clock-AF_IPX" , "clock-AF_APPLETALK",
"clock-AF_NETROM", "clock-AF_BRIDGE" , "clock-AF_ATMPVC" ,
"clock-AF_X25" , "clock-AF_INET6" , "clock-AF_ROSE" ,
"clock-AF_DECnet", "clock-AF_NETBEUI" , "clock-AF_SECURITY" ,
"clock-AF_KEY" , "clock-AF_NETLINK" , "clock-AF_PACKET" ,
"clock-AF_ASH" , "clock-AF_ECONET" , "clock-AF_ATMSVC" ,
"clock-AF_RDS" , "clock-AF_SNA" , "clock-AF_IRDA" ,
"clock-AF_PPPOX" , "clock-AF_WANPIPE" , "clock-AF_LLC" ,
"clock-27" , "clock-28" , "clock-AF_CAN" ,
"clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" ,
"clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" ,
"clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" ,
"clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_MAX"
};
/*
* sk_callback_lock locking rules are per-address-family,
* so split the lock classes by using a per-AF key:
*/
static struct lock_class_key af_callback_keys[AF_MAX];
/* Take into consideration the size of the struct sk_buff overhead in the
* determination of these values, since that is non-constant across
* platforms. This makes socket queueing behavior and performance
* not depend upon such differences.
*/
#define _SK_MEM_PACKETS 256
#define _SK_MEM_OVERHEAD SKB_TRUESIZE(256)
#define SK_WMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
#define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
/* Run time adjustable parameters. */
__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX;
EXPORT_SYMBOL(sysctl_wmem_max);
__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX;
EXPORT_SYMBOL(sysctl_rmem_max);
__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
/* Maximal space eaten by iovec or ancillary data plus some space */
int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
EXPORT_SYMBOL(sysctl_optmem_max);
int sysctl_tstamp_allow_data __read_mostly = 1;
struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE;
EXPORT_SYMBOL_GPL(memalloc_socks);
/**
* sk_set_memalloc - sets %SOCK_MEMALLOC
* @sk: socket to set it on
*
* Set %SOCK_MEMALLOC on a socket for access to emergency reserves.
* It's the responsibility of the admin to adjust min_free_kbytes
* to meet the requirements
*/
void sk_set_memalloc(struct sock *sk)
{
sock_set_flag(sk, SOCK_MEMALLOC);
sk->sk_allocation |= __GFP_MEMALLOC;
static_key_slow_inc(&memalloc_socks);
}
EXPORT_SYMBOL_GPL(sk_set_memalloc);
void sk_clear_memalloc(struct sock *sk)
{
sock_reset_flag(sk, SOCK_MEMALLOC);
sk->sk_allocation &= ~__GFP_MEMALLOC;
static_key_slow_dec(&memalloc_socks);
netvm: prevent a stream-specific deadlock This patch series is based on top of "Swap-over-NBD without deadlocking v15" as it depends on the same reservation of PF_MEMALLOC reserves logic. When a user or administrator requires swap for their application, they create a swap partition and file, format it with mkswap and activate it with swapon. In diskless systems this is not an option so if swap if required then swapping over the network is considered. The two likely scenarios are when blade servers are used as part of a cluster where the form factor or maintenance costs do not allow the use of disks and thin clients. The Linux Terminal Server Project recommends the use of the Network Block Device (NBD) for swap but this is not always an option. There is no guarantee that the network attached storage (NAS) device is running Linux or supports NBD. However, it is likely that it supports NFS so there are users that want support for swapping over NFS despite any performance concern. Some distributions currently carry patches that support swapping over NFS but it would be preferable to support it in the mainline kernel. Patch 1 avoids a stream-specific deadlock that potentially affects TCP. Patch 2 is a small modification to SELinux to avoid using PFMEMALLOC reserves. Patch 3 adds three helpers for filesystems to handle swap cache pages. For example, page_file_mapping() returns page->mapping for file-backed pages and the address_space of the underlying swap file for swap cache pages. Patch 4 adds two address_space_operations to allow a filesystem to pin all metadata relevant to a swapfile in memory. Upon successful activation, the swapfile is marked SWP_FILE and the address space operation ->direct_IO is used for writing and ->readpage for reading in swap pages. Patch 5 notes that patch 3 is bolting filesystem-specific-swapfile-support onto the side and that the default handlers have different information to what is available to the filesystem. This patch refactors the code so that there are generic handlers for each of the new address_space operations. Patch 6 adds an API to allow a vector of kernel addresses to be translated to struct pages and pinned for IO. Patch 7 adds support for using highmem pages for swap by kmapping the pages before calling the direct_IO handler. Patch 8 updates NFS to use the helpers from patch 3 where necessary. Patch 9 avoids setting PF_private on PG_swapcache pages within NFS. Patch 10 implements the new swapfile-related address_space operations for NFS and teaches the direct IO handler how to manage kernel addresses. Patch 11 prevents page allocator recursions in NFS by using GFP_NOIO where appropriate. Patch 12 fixes a NULL pointer dereference that occurs when using swap-over-NFS. With the patches applied, it is possible to mount a swapfile that is on an NFS filesystem. Swap performance is not great with a swap stress test taking roughly twice as long to complete than if the swap device was backed by NBD. This patch: netvm: prevent a stream-specific deadlock It could happen that all !SOCK_MEMALLOC sockets have buffered so much data that we're over the global rmem limit. This will prevent SOCK_MEMALLOC buffers from receiving data, which will prevent userspace from running, which is needed to reduce the buffered data. Fix this by exempting the SOCK_MEMALLOC sockets from the rmem limit. Once this change it applied, it is important that sockets that set SOCK_MEMALLOC do not clear the flag until the socket is being torn down. If this happens, a warning is generated and the tokens reclaimed to avoid accounting errors until the bug is fixed. [davem@davemloft.net: Warning about clearing SOCK_MEMALLOC] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Rik van Riel <riel@redhat.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: Neil Brown <neilb@suse.de> Cc: Christoph Hellwig <hch@infradead.org> Cc: Mike Christie <michaelc@cs.wisc.edu> Cc: Eric B Munson <emunson@mgebm.net> Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 06:44:41 +07:00
/*
* SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward
net, swap: Remove a warning and clarify why sk_mem_reclaim is required when deactivating swap Jeff Layton reported the following; [ 74.232485] ------------[ cut here ]------------ [ 74.233354] WARNING: CPU: 2 PID: 754 at net/core/sock.c:364 sk_clear_memalloc+0x51/0x80() [ 74.234790] Modules linked in: cts rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache xfs libcrc32c snd_hda_codec_generic snd_hda_intel snd_hda_controller snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device nfsd snd_pcm snd_timer snd e1000 ppdev parport_pc joydev parport pvpanic soundcore floppy serio_raw i2c_piix4 pcspkr nfs_acl lockd virtio_balloon acpi_cpufreq auth_rpcgss grace sunrpc qxl drm_kms_helper ttm drm virtio_console virtio_blk virtio_pci ata_generic virtio_ring pata_acpi virtio [ 74.243599] CPU: 2 PID: 754 Comm: swapoff Not tainted 4.1.0-rc6+ #5 [ 74.244635] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 74.245546] 0000000000000000 0000000079e69e31 ffff8800d066bde8 ffffffff8179263d [ 74.246786] 0000000000000000 0000000000000000 ffff8800d066be28 ffffffff8109e6fa [ 74.248175] 0000000000000000 ffff880118d48000 ffff8800d58f5c08 ffff880036e380a8 [ 74.249483] Call Trace: [ 74.249872] [<ffffffff8179263d>] dump_stack+0x45/0x57 [ 74.250703] [<ffffffff8109e6fa>] warn_slowpath_common+0x8a/0xc0 [ 74.251655] [<ffffffff8109e82a>] warn_slowpath_null+0x1a/0x20 [ 74.252585] [<ffffffff81661241>] sk_clear_memalloc+0x51/0x80 [ 74.253519] [<ffffffffa0116c72>] xs_disable_swap+0x42/0x80 [sunrpc] [ 74.254537] [<ffffffffa01109de>] rpc_clnt_swap_deactivate+0x7e/0xc0 [sunrpc] [ 74.255610] [<ffffffffa03e4fd7>] nfs_swap_deactivate+0x27/0x30 [nfs] [ 74.256582] [<ffffffff811e99d4>] destroy_swap_extents+0x74/0x80 [ 74.257496] [<ffffffff811ecb52>] SyS_swapoff+0x222/0x5c0 [ 74.258318] [<ffffffff81023f27>] ? syscall_trace_leave+0xc7/0x140 [ 74.259253] [<ffffffff81798dae>] system_call_fastpath+0x12/0x71 [ 74.260158] ---[ end trace 2530722966429f10 ]--- The warning in question was unnecessary but with Jeff's series the rules are also clearer. This patch removes the warning and updates the comment to explain why sk_mem_reclaim() may still be called. [jlayton: remove if (sk->sk_forward_alloc) conditional. As Leon points out that it's not needed.] Cc: Leon Romanovsky <leon@leon.nu> Signed-off-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Jeff Layton <jeff.layton@primarydata.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-11 08:02:04 +07:00
* progress of swapping. SOCK_MEMALLOC may be cleared while
* it has rmem allocations due to the last swapfile being deactivated
* but there is a risk that the socket is unusable due to exceeding
* the rmem limits. Reclaim the reserves and obey rmem limits again.
netvm: prevent a stream-specific deadlock This patch series is based on top of "Swap-over-NBD without deadlocking v15" as it depends on the same reservation of PF_MEMALLOC reserves logic. When a user or administrator requires swap for their application, they create a swap partition and file, format it with mkswap and activate it with swapon. In diskless systems this is not an option so if swap if required then swapping over the network is considered. The two likely scenarios are when blade servers are used as part of a cluster where the form factor or maintenance costs do not allow the use of disks and thin clients. The Linux Terminal Server Project recommends the use of the Network Block Device (NBD) for swap but this is not always an option. There is no guarantee that the network attached storage (NAS) device is running Linux or supports NBD. However, it is likely that it supports NFS so there are users that want support for swapping over NFS despite any performance concern. Some distributions currently carry patches that support swapping over NFS but it would be preferable to support it in the mainline kernel. Patch 1 avoids a stream-specific deadlock that potentially affects TCP. Patch 2 is a small modification to SELinux to avoid using PFMEMALLOC reserves. Patch 3 adds three helpers for filesystems to handle swap cache pages. For example, page_file_mapping() returns page->mapping for file-backed pages and the address_space of the underlying swap file for swap cache pages. Patch 4 adds two address_space_operations to allow a filesystem to pin all metadata relevant to a swapfile in memory. Upon successful activation, the swapfile is marked SWP_FILE and the address space operation ->direct_IO is used for writing and ->readpage for reading in swap pages. Patch 5 notes that patch 3 is bolting filesystem-specific-swapfile-support onto the side and that the default handlers have different information to what is available to the filesystem. This patch refactors the code so that there are generic handlers for each of the new address_space operations. Patch 6 adds an API to allow a vector of kernel addresses to be translated to struct pages and pinned for IO. Patch 7 adds support for using highmem pages for swap by kmapping the pages before calling the direct_IO handler. Patch 8 updates NFS to use the helpers from patch 3 where necessary. Patch 9 avoids setting PF_private on PG_swapcache pages within NFS. Patch 10 implements the new swapfile-related address_space operations for NFS and teaches the direct IO handler how to manage kernel addresses. Patch 11 prevents page allocator recursions in NFS by using GFP_NOIO where appropriate. Patch 12 fixes a NULL pointer dereference that occurs when using swap-over-NFS. With the patches applied, it is possible to mount a swapfile that is on an NFS filesystem. Swap performance is not great with a swap stress test taking roughly twice as long to complete than if the swap device was backed by NBD. This patch: netvm: prevent a stream-specific deadlock It could happen that all !SOCK_MEMALLOC sockets have buffered so much data that we're over the global rmem limit. This will prevent SOCK_MEMALLOC buffers from receiving data, which will prevent userspace from running, which is needed to reduce the buffered data. Fix this by exempting the SOCK_MEMALLOC sockets from the rmem limit. Once this change it applied, it is important that sockets that set SOCK_MEMALLOC do not clear the flag until the socket is being torn down. If this happens, a warning is generated and the tokens reclaimed to avoid accounting errors until the bug is fixed. [davem@davemloft.net: Warning about clearing SOCK_MEMALLOC] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Rik van Riel <riel@redhat.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: Neil Brown <neilb@suse.de> Cc: Christoph Hellwig <hch@infradead.org> Cc: Mike Christie <michaelc@cs.wisc.edu> Cc: Eric B Munson <emunson@mgebm.net> Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 06:44:41 +07:00
*/
net, swap: Remove a warning and clarify why sk_mem_reclaim is required when deactivating swap Jeff Layton reported the following; [ 74.232485] ------------[ cut here ]------------ [ 74.233354] WARNING: CPU: 2 PID: 754 at net/core/sock.c:364 sk_clear_memalloc+0x51/0x80() [ 74.234790] Modules linked in: cts rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache xfs libcrc32c snd_hda_codec_generic snd_hda_intel snd_hda_controller snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device nfsd snd_pcm snd_timer snd e1000 ppdev parport_pc joydev parport pvpanic soundcore floppy serio_raw i2c_piix4 pcspkr nfs_acl lockd virtio_balloon acpi_cpufreq auth_rpcgss grace sunrpc qxl drm_kms_helper ttm drm virtio_console virtio_blk virtio_pci ata_generic virtio_ring pata_acpi virtio [ 74.243599] CPU: 2 PID: 754 Comm: swapoff Not tainted 4.1.0-rc6+ #5 [ 74.244635] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 74.245546] 0000000000000000 0000000079e69e31 ffff8800d066bde8 ffffffff8179263d [ 74.246786] 0000000000000000 0000000000000000 ffff8800d066be28 ffffffff8109e6fa [ 74.248175] 0000000000000000 ffff880118d48000 ffff8800d58f5c08 ffff880036e380a8 [ 74.249483] Call Trace: [ 74.249872] [<ffffffff8179263d>] dump_stack+0x45/0x57 [ 74.250703] [<ffffffff8109e6fa>] warn_slowpath_common+0x8a/0xc0 [ 74.251655] [<ffffffff8109e82a>] warn_slowpath_null+0x1a/0x20 [ 74.252585] [<ffffffff81661241>] sk_clear_memalloc+0x51/0x80 [ 74.253519] [<ffffffffa0116c72>] xs_disable_swap+0x42/0x80 [sunrpc] [ 74.254537] [<ffffffffa01109de>] rpc_clnt_swap_deactivate+0x7e/0xc0 [sunrpc] [ 74.255610] [<ffffffffa03e4fd7>] nfs_swap_deactivate+0x27/0x30 [nfs] [ 74.256582] [<ffffffff811e99d4>] destroy_swap_extents+0x74/0x80 [ 74.257496] [<ffffffff811ecb52>] SyS_swapoff+0x222/0x5c0 [ 74.258318] [<ffffffff81023f27>] ? syscall_trace_leave+0xc7/0x140 [ 74.259253] [<ffffffff81798dae>] system_call_fastpath+0x12/0x71 [ 74.260158] ---[ end trace 2530722966429f10 ]--- The warning in question was unnecessary but with Jeff's series the rules are also clearer. This patch removes the warning and updates the comment to explain why sk_mem_reclaim() may still be called. [jlayton: remove if (sk->sk_forward_alloc) conditional. As Leon points out that it's not needed.] Cc: Leon Romanovsky <leon@leon.nu> Signed-off-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Jeff Layton <jeff.layton@primarydata.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-11 08:02:04 +07:00
sk_mem_reclaim(sk);
}
EXPORT_SYMBOL_GPL(sk_clear_memalloc);
int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
int ret;
unsigned long pflags = current->flags;
/* these should have been dropped before queueing */
BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));
current->flags |= PF_MEMALLOC;
ret = sk->sk_backlog_rcv(sk, skb);
tsk_restore_flags(current, pflags, PF_MEMALLOC);
return ret;
}
EXPORT_SYMBOL(__sk_backlog_rcv);
static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
{
struct timeval tv;
if (optlen < sizeof(tv))
return -EINVAL;
if (copy_from_user(&tv, optval, sizeof(tv)))
return -EFAULT;
if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC)
return -EDOM;
if (tv.tv_sec < 0) {
static int warned __read_mostly;
*timeo_p = 0;
if (warned < 10 && net_ratelimit()) {
warned++;
pr_info("%s: `%s' (pid %d) tries to set negative timeout\n",
__func__, current->comm, task_pid_nr(current));
}
return 0;
}
*timeo_p = MAX_SCHEDULE_TIMEOUT;
if (tv.tv_sec == 0 && tv.tv_usec == 0)
return 0;
if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT/HZ - 1))
*timeo_p = tv.tv_sec*HZ + (tv.tv_usec+(1000000/HZ-1))/(1000000/HZ);
return 0;
}
static void sock_warn_obsolete_bsdism(const char *name)
{
static int warned;
static char warncomm[TASK_COMM_LEN];
if (strcmp(warncomm, current->comm) && warned < 5) {
strcpy(warncomm, current->comm);
pr_warn("process `%s' is using obsolete %s SO_BSDCOMPAT\n",
warncomm, name);
warned++;
}
}
#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
{
if (sk->sk_flags & flags) {
sk->sk_flags &= ~flags;
if (!(sk->sk_flags & SK_FLAGS_TIMESTAMP))
net_disable_timestamp();
}
}
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:08:21 +07:00
int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
int err;
net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-13 03:26:31 +07:00
unsigned long flags;
struct sk_buff_head *list = &sk->sk_receive_queue;
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:08:21 +07:00
if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) {
atomic_inc(&sk->sk_drops);
trace_sock_rcvqueue_full(sk, skb);
return -ENOMEM;
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:08:21 +07:00
}
err = sk_filter(sk, skb);
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:08:21 +07:00
if (err)
return err;
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:08:21 +07:00
netvm: prevent a stream-specific deadlock This patch series is based on top of "Swap-over-NBD without deadlocking v15" as it depends on the same reservation of PF_MEMALLOC reserves logic. When a user or administrator requires swap for their application, they create a swap partition and file, format it with mkswap and activate it with swapon. In diskless systems this is not an option so if swap if required then swapping over the network is considered. The two likely scenarios are when blade servers are used as part of a cluster where the form factor or maintenance costs do not allow the use of disks and thin clients. The Linux Terminal Server Project recommends the use of the Network Block Device (NBD) for swap but this is not always an option. There is no guarantee that the network attached storage (NAS) device is running Linux or supports NBD. However, it is likely that it supports NFS so there are users that want support for swapping over NFS despite any performance concern. Some distributions currently carry patches that support swapping over NFS but it would be preferable to support it in the mainline kernel. Patch 1 avoids a stream-specific deadlock that potentially affects TCP. Patch 2 is a small modification to SELinux to avoid using PFMEMALLOC reserves. Patch 3 adds three helpers for filesystems to handle swap cache pages. For example, page_file_mapping() returns page->mapping for file-backed pages and the address_space of the underlying swap file for swap cache pages. Patch 4 adds two address_space_operations to allow a filesystem to pin all metadata relevant to a swapfile in memory. Upon successful activation, the swapfile is marked SWP_FILE and the address space operation ->direct_IO is used for writing and ->readpage for reading in swap pages. Patch 5 notes that patch 3 is bolting filesystem-specific-swapfile-support onto the side and that the default handlers have different information to what is available to the filesystem. This patch refactors the code so that there are generic handlers for each of the new address_space operations. Patch 6 adds an API to allow a vector of kernel addresses to be translated to struct pages and pinned for IO. Patch 7 adds support for using highmem pages for swap by kmapping the pages before calling the direct_IO handler. Patch 8 updates NFS to use the helpers from patch 3 where necessary. Patch 9 avoids setting PF_private on PG_swapcache pages within NFS. Patch 10 implements the new swapfile-related address_space operations for NFS and teaches the direct IO handler how to manage kernel addresses. Patch 11 prevents page allocator recursions in NFS by using GFP_NOIO where appropriate. Patch 12 fixes a NULL pointer dereference that occurs when using swap-over-NFS. With the patches applied, it is possible to mount a swapfile that is on an NFS filesystem. Swap performance is not great with a swap stress test taking roughly twice as long to complete than if the swap device was backed by NBD. This patch: netvm: prevent a stream-specific deadlock It could happen that all !SOCK_MEMALLOC sockets have buffered so much data that we're over the global rmem limit. This will prevent SOCK_MEMALLOC buffers from receiving data, which will prevent userspace from running, which is needed to reduce the buffered data. Fix this by exempting the SOCK_MEMALLOC sockets from the rmem limit. Once this change it applied, it is important that sockets that set SOCK_MEMALLOC do not clear the flag until the socket is being torn down. If this happens, a warning is generated and the tokens reclaimed to avoid accounting errors until the bug is fixed. [davem@davemloft.net: Warning about clearing SOCK_MEMALLOC] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Rik van Riel <riel@redhat.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: Neil Brown <neilb@suse.de> Cc: Christoph Hellwig <hch@infradead.org> Cc: Mike Christie <michaelc@cs.wisc.edu> Cc: Eric B Munson <emunson@mgebm.net> Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 06:44:41 +07:00
if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
atomic_inc(&sk->sk_drops);
return -ENOBUFS;
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 15:11:19 +07:00
}
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:08:21 +07:00
skb->dev = NULL;
skb_set_owner_r(skb, sk);
/* we escape from rcu protected region, make sure we dont leak
* a norefcounted dst
*/
skb_dst_force(skb);
net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-13 03:26:31 +07:00
spin_lock_irqsave(&list->lock, flags);
sock_skb_set_dropcount(sk, skb);
net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-13 03:26:31 +07:00
__skb_queue_tail(list, skb);
spin_unlock_irqrestore(&list->lock, flags);
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:08:21 +07:00
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_data_ready(sk);
return 0;
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:08:21 +07:00
}
EXPORT_SYMBOL(sock_queue_rcv_skb);
int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested)
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:08:21 +07:00
{
int rc = NET_RX_SUCCESS;
if (sk_filter(sk, skb))
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:08:21 +07:00
goto discard_and_relse;
skb->dev = NULL;
if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) {
atomic_inc(&sk->sk_drops);
goto discard_and_relse;
}
if (nested)
bh_lock_sock_nested(sk);
else
bh_lock_sock(sk);
if (!sock_owned_by_user(sk)) {
/*
* trylock + unlock semantics:
*/
mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_);
rc = sk_backlog_rcv(sk, skb);
mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
} else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) {
net: add limit for socket backlog We got system OOM while running some UDP netperf testing on the loopback device. The case is multiple senders sent stream UDP packets to a single receiver via loopback on local host. Of course, the receiver is not able to handle all the packets in time. But we surprisingly found that these packets were not discarded due to the receiver's sk->sk_rcvbuf limit. Instead, they are kept queuing to sk->sk_backlog and finally ate up all the memory. We believe this is a secure hole that a none privileged user can crash the system. The root cause for this problem is, when the receiver is doing __release_sock() (i.e. after userspace recv, kernel udp_recvmsg -> skb_free_datagram_locked -> release_sock), it moves skbs from backlog to sk_receive_queue with the softirq enabled. In the above case, multiple busy senders will almost make it an endless loop. The skbs in the backlog end up eat all the system memory. The issue is not only for UDP. Any protocols using socket backlog is potentially affected. The patch adds limit for socket backlog so that the backlog size cannot be expanded endlessly. Reported-by: Alex Shi <alex.shi@intel.com> Cc: David Miller <davem@davemloft.net> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru Cc: "Pekka Savola (ipv6)" <pekkas@netcore.fi> Cc: Patrick McHardy <kaber@trash.net> Cc: Vlad Yasevich <vladislav.yasevich@hp.com> Cc: Sridhar Samudrala <sri@us.ibm.com> Cc: Jon Maloy <jon.maloy@ericsson.com> Cc: Allan Stephens <allan.stephens@windriver.com> Cc: Andrew Hendry <andrew.hendry@gmail.com> Signed-off-by: Zhu Yi <yi.zhu@intel.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-03-05 01:01:40 +07:00
bh_unlock_sock(sk);
atomic_inc(&sk->sk_drops);
goto discard_and_relse;
}
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:08:21 +07:00
bh_unlock_sock(sk);
out:
sock_put(sk);
return rc;
discard_and_relse:
kfree_skb(skb);
goto out;
}
EXPORT_SYMBOL(sk_receive_skb);
struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
{
struct dst_entry *dst = __sk_dst_get(sk);
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:08:21 +07:00
if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
sk_tx_queue_clear(sk);
RCU_INIT_POINTER(sk->sk_dst_cache, NULL);
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:08:21 +07:00
dst_release(dst);
return NULL;
}
return dst;
}
EXPORT_SYMBOL(__sk_dst_check);
struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie)
{
struct dst_entry *dst = sk_dst_get(sk);
if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
sk_dst_reset(sk);
dst_release(dst);
return NULL;
}
return dst;
}
EXPORT_SYMBOL(sk_dst_check);
static int sock_setbindtodevice(struct sock *sk, char __user *optval,
int optlen)
{
int ret = -ENOPROTOOPT;
#ifdef CONFIG_NETDEVICES
struct net *net = sock_net(sk);
char devname[IFNAMSIZ];
int index;
/* Sorry... */
ret = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_RAW))
goto out;
ret = -EINVAL;
if (optlen < 0)
goto out;
/* Bind this socket to a particular device like "eth0",
* as specified in the passed interface name. If the
* name is "" or the option length is zero the socket
* is not bound.
*/
if (optlen > IFNAMSIZ - 1)
optlen = IFNAMSIZ - 1;
memset(devname, 0, sizeof(devname));
ret = -EFAULT;
if (copy_from_user(devname, optval, optlen))
goto out;
index = 0;
if (devname[0] != '\0') {
struct net_device *dev;
rcu_read_lock();
dev = dev_get_by_name_rcu(net, devname);
if (dev)
index = dev->ifindex;
rcu_read_unlock();
ret = -ENODEV;
if (!dev)
goto out;
}
lock_sock(sk);
sk->sk_bound_dev_if = index;
sk_dst_reset(sk);
release_sock(sk);
ret = 0;
out:
#endif
return ret;
}
static int sock_getbindtodevice(struct sock *sk, char __user *optval,
int __user *optlen, int len)
{
int ret = -ENOPROTOOPT;
#ifdef CONFIG_NETDEVICES
struct net *net = sock_net(sk);
char devname[IFNAMSIZ];
if (sk->sk_bound_dev_if == 0) {
len = 0;
goto zero;
}
ret = -EINVAL;
if (len < IFNAMSIZ)
goto out;
ret = netdev_get_name(net, devname, sk->sk_bound_dev_if);
if (ret)
goto out;
len = strlen(devname) + 1;
ret = -EFAULT;
if (copy_to_user(optval, devname, len))
goto out;
zero:
ret = -EFAULT;
if (put_user(len, optlen))
goto out;
ret = 0;
out:
#endif
return ret;
}
static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
{
if (valbool)
sock_set_flag(sk, bit);
else
sock_reset_flag(sk, bit);
}
bool sk_mc_loop(struct sock *sk)
{
if (dev_recursion_level())
return false;
if (!sk)
return true;
switch (sk->sk_family) {
case AF_INET:
return inet_sk(sk)->mc_loop;
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
return inet6_sk(sk)->mc_loop;
#endif
}
WARN_ON(1);
return true;
}
EXPORT_SYMBOL(sk_mc_loop);
/*
* This is meant for all protocols to use and covers goings on
* at the socket level. Everything here is generic.
*/
int sock_setsockopt(struct socket *sock, int level, int optname,
char __user *optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
int val;
int valbool;
struct linger ling;
int ret = 0;
/*
* Options without arguments
*/
if (optname == SO_BINDTODEVICE)
return sock_setbindtodevice(sk, optval, optlen);
if (optlen < sizeof(int))
return -EINVAL;
if (get_user(val, (int __user *)optval))
return -EFAULT;
valbool = val ? 1 : 0;
lock_sock(sk);
switch (optname) {
case SO_DEBUG:
if (val && !capable(CAP_NET_ADMIN))
ret = -EACCES;
else
sock_valbool_flag(sk, SOCK_DBG, valbool);
break;
case SO_REUSEADDR:
sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE);
break;
case SO_REUSEPORT:
sk->sk_reuseport = valbool;
break;
case SO_TYPE:
case SO_PROTOCOL:
case SO_DOMAIN:
case SO_ERROR:
ret = -ENOPROTOOPT;
break;
case SO_DONTROUTE:
sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool);
break;
case SO_BROADCAST:
sock_valbool_flag(sk, SOCK_BROADCAST, valbool);
break;
case SO_SNDBUF:
/* Don't error on this BSD doesn't and if you think
* about it this is right. Otherwise apps have to
* play 'guess the biggest size' games. RCVBUF/SNDBUF
* are treated in BSD as hints
*/
val = min_t(u32, val, sysctl_wmem_max);
set_sndbuf:
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
sk->sk_sndbuf = max_t(u32, val * 2, SOCK_MIN_SNDBUF);
/* Wake up sending tasks if we upped the value. */
sk->sk_write_space(sk);
break;
case SO_SNDBUFFORCE:
if (!capable(CAP_NET_ADMIN)) {
ret = -EPERM;
break;
}
goto set_sndbuf;
case SO_RCVBUF:
/* Don't error on this BSD doesn't and if you think
* about it this is right. Otherwise apps have to
* play 'guess the biggest size' games. RCVBUF/SNDBUF
* are treated in BSD as hints
*/
val = min_t(u32, val, sysctl_rmem_max);
set_rcvbuf:
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
/*
* We double it on the way in to account for
* "struct sk_buff" etc. overhead. Applications
* assume that the SO_RCVBUF setting they make will
* allow that much actual data to be received on that
* socket.
*
* Applications are unaware that "struct sk_buff" and
* other overheads allocate from the receive buffer
* during socket buffer allocation.
*
* And after considering the possible alternatives,
* returning the value we actually used in getsockopt
* is the most desirable behavior.
*/
sk->sk_rcvbuf = max_t(u32, val * 2, SOCK_MIN_RCVBUF);
break;
case SO_RCVBUFFORCE:
if (!capable(CAP_NET_ADMIN)) {
ret = -EPERM;
break;
}
goto set_rcvbuf;
case SO_KEEPALIVE:
#ifdef CONFIG_INET
if (sk->sk_protocol == IPPROTO_TCP &&
sk->sk_type == SOCK_STREAM)
tcp_set_keepalive(sk, valbool);
#endif
sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
break;
case SO_OOBINLINE:
sock_valbool_flag(sk, SOCK_URGINLINE, valbool);
break;
case SO_NO_CHECK:
sk->sk_no_check_tx = valbool;
break;
case SO_PRIORITY:
if ((val >= 0 && val <= 6) ||
ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
sk->sk_priority = val;
else
ret = -EPERM;
break;
case SO_LINGER:
if (optlen < sizeof(ling)) {
ret = -EINVAL; /* 1003.1g */
break;
}
if (copy_from_user(&ling, optval, sizeof(ling))) {
ret = -EFAULT;
break;
}
if (!ling.l_onoff)
sock_reset_flag(sk, SOCK_LINGER);
else {
#if (BITS_PER_LONG == 32)
if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ)
sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT;
else
#endif
sk->sk_lingertime = (unsigned int)ling.l_linger * HZ;
sock_set_flag(sk, SOCK_LINGER);
}
break;
case SO_BSDCOMPAT:
sock_warn_obsolete_bsdism("setsockopt");
break;
case SO_PASSCRED:
if (valbool)
set_bit(SOCK_PASSCRED, &sock->flags);
else
clear_bit(SOCK_PASSCRED, &sock->flags);
break;
case SO_TIMESTAMP:
case SO_TIMESTAMPNS:
if (valbool) {
if (optname == SO_TIMESTAMP)
sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
else
sock_set_flag(sk, SOCK_RCVTSTAMPNS);
sock_set_flag(sk, SOCK_RCVTSTAMP);
sock_enable_timestamp(sk, SOCK_TIMESTAMP);
} else {
sock_reset_flag(sk, SOCK_RCVTSTAMP);
sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
}
break;
case SO_TIMESTAMPING:
if (val & ~SOF_TIMESTAMPING_MASK) {
ret = -EINVAL;
break;
}
if (val & SOF_TIMESTAMPING_OPT_ID &&
net-timestamp: TCP timestamping TCP timestamping extends SO_TIMESTAMPING to bytestreams. Bytestreams do not have a 1:1 relationship between send() buffers and network packets. The feature interprets a send call on a bytestream as a request for a timestamp for the last byte in that send() buffer. The choice corresponds to a request for a timestamp when all bytes in the buffer have been sent. That assumption depends on in-order kernel transmission. This is the common case. That said, it is possible to construct a traffic shaping tree that would result in reordering. The guarantee is strong, then, but not ironclad. This implementation supports send and sendpages (splice). GSO replaces one large packet with multiple smaller packets. This patch also copies the option into the correct smaller packet. This patch does not yet support timestamping on data in an initial TCP Fast Open SYN, because that takes a very different data path. If ID generation in ee_data is enabled, bytestream timestamps return a byte offset, instead of the packet counter for datagrams. The implementation supports a single timestamp per packet. It silenty replaces requests for previous timestamps. To avoid missing tstamps, flush the tcp queue by disabling Nagle, cork and autocork. Missing tstamps can be detected by offset when the ee_data ID is enabled. Implementation details: - On GSO, the timestamping code can be included in the main loop. I moved it into its own loop to reduce the impact on the common case to a single branch. - To avoid leaking the absolute seqno to userspace, the offset returned in ee_data must always be relative. It is an offset between an skb and sk field. The first is always set (also for GSO & ACK). The second must also never be uninitialized. Only allow the ID option on sockets in the ESTABLISHED state, for which the seqno is available. Never reset it to zero (instead, move it to the current seqno when reenabling the option). Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-05 09:11:49 +07:00
!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
if (sk->sk_protocol == IPPROTO_TCP) {
if (sk->sk_state != TCP_ESTABLISHED) {
ret = -EINVAL;
break;
}
sk->sk_tskey = tcp_sk(sk)->snd_una;
} else {
sk->sk_tskey = 0;
}
}
sk->sk_tsflags = val;
if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
sock_enable_timestamp(sk,
SOCK_TIMESTAMPING_RX_SOFTWARE);
else
sock_disable_timestamp(sk,
(1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
break;
case SO_RCVLOWAT:
if (val < 0)
val = INT_MAX;
sk->sk_rcvlowat = val ? : 1;
break;
case SO_RCVTIMEO:
ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen);
break;
case SO_SNDTIMEO:
ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen);
break;
case SO_ATTACH_FILTER:
ret = -EINVAL;
if (optlen == sizeof(struct sock_fprog)) {
struct sock_fprog fprog;
ret = -EFAULT;
if (copy_from_user(&fprog, optval, sizeof(fprog)))
break;
ret = sk_attach_filter(&fprog, sk);
}
break;
case SO_ATTACH_BPF:
ret = -EINVAL;
if (optlen == sizeof(u32)) {
u32 ufd;
ret = -EFAULT;
if (copy_from_user(&ufd, optval, sizeof(ufd)))
break;
ret = sk_attach_bpf(ufd, sk);
}
break;
case SO_DETACH_FILTER:
ret = sk_detach_filter(sk);
break;
case SO_LOCK_FILTER:
if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool)
ret = -EPERM;
else
sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool);
break;
case SO_PASSSEC:
if (valbool)
set_bit(SOCK_PASSSEC, &sock->flags);
else
clear_bit(SOCK_PASSSEC, &sock->flags);
break;
case SO_MARK:
if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
ret = -EPERM;
else
sk->sk_mark = val;
break;
[AF_UNIX]: Datagram getpeersec This patch implements an API whereby an application can determine the label of its peer's Unix datagram sockets via the auxiliary data mechanism of recvmsg. Patch purpose: This patch enables a security-aware application to retrieve the security context of the peer of a Unix datagram socket. The application can then use this security context to determine the security context for processing on behalf of the peer who sent the packet. Patch design and implementation: The design and implementation is very similar to the UDP case for INET sockets. Basically we build upon the existing Unix domain socket API for retrieving user credentials. Linux offers the API for obtaining user credentials via ancillary messages (i.e., out of band/control messages that are bundled together with a normal message). To retrieve the security context, the application first indicates to the kernel such desire by setting the SO_PASSSEC option via getsockopt. Then the application retrieves the security context using the auxiliary data mechanism. An example server application for Unix datagram socket should look like this: toggle = 1; toggle_len = sizeof(toggle); setsockopt(sockfd, SOL_SOCKET, SO_PASSSEC, &toggle, &toggle_len); recvmsg(sockfd, &msg_hdr, 0); if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) { cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr); if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) && cmsg_hdr->cmsg_level == SOL_SOCKET && cmsg_hdr->cmsg_type == SCM_SECURITY) { memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext)); } } sock_setsockopt is enhanced with a new socket option SOCK_PASSSEC to allow a server socket to receive security context of the peer. Testing: We have tested the patch by setting up Unix datagram client and server applications. We verified that the server can retrieve the security context using the auxiliary data mechanism of recvmsg. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Acked-by: Acked-by: James Morris <jmorris@namei.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-30 02:27:47 +07:00
net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-13 03:26:31 +07:00
case SO_RXQ_OVFL:
sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool);
net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-13 03:26:31 +07:00
break;
case SO_WIFI_STATUS:
sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool);
break;
case SO_PEEK_OFF:
if (sock->ops->set_peek_off)
ret = sock->ops->set_peek_off(sk, val);
else
ret = -EOPNOTSUPP;
break;
case SO_NOFCS:
sock_valbool_flag(sk, SOCK_NOFCS, valbool);
break;
case SO_SELECT_ERR_QUEUE:
sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool);
break;
#ifdef CONFIG_NET_RX_BUSY_POLL
case SO_BUSY_POLL:
/* allow unprivileged users to decrease the value */
if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN))
ret = -EPERM;
else {
if (val < 0)
ret = -EINVAL;
else
sk->sk_ll_usec = val;
}
break;
#endif
case SO_MAX_PACING_RATE:
sk->sk_max_pacing_rate = val;
sk->sk_pacing_rate = min(sk->sk_pacing_rate,
sk->sk_max_pacing_rate);
break;
default:
ret = -ENOPROTOOPT;
break;
}
release_sock(sk);
return ret;
}
EXPORT_SYMBOL(sock_setsockopt);
static void cred_to_ucred(struct pid *pid, const struct cred *cred,
struct ucred *ucred)
{
ucred->pid = pid_vnr(pid);
ucred->uid = ucred->gid = -1;
if (cred) {
struct user_namespace *current_ns = current_user_ns();
ucred->uid = from_kuid_munged(current_ns, cred->euid);
ucred->gid = from_kgid_munged(current_ns, cred->egid);
}
}
int sock_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen)
{
struct sock *sk = sock->sk;
union {
int val;
struct linger ling;
struct timeval tm;
} v;
int lv = sizeof(int);
int len;
if (get_user(len, optlen))
return -EFAULT;
if (len < 0)
return -EINVAL;
memset(&v, 0, sizeof(v));
switch (optname) {
case SO_DEBUG:
v.val = sock_flag(sk, SOCK_DBG);
break;
case SO_DONTROUTE:
v.val = sock_flag(sk, SOCK_LOCALROUTE);
break;
case SO_BROADCAST:
v.val = sock_flag(sk, SOCK_BROADCAST);
break;
case SO_SNDBUF:
v.val = sk->sk_sndbuf;
break;
case SO_RCVBUF:
v.val = sk->sk_rcvbuf;
break;
case SO_REUSEADDR:
v.val = sk->sk_reuse;
break;
case SO_REUSEPORT:
v.val = sk->sk_reuseport;
break;
case SO_KEEPALIVE:
v.val = sock_flag(sk, SOCK_KEEPOPEN);
break;
case SO_TYPE:
v.val = sk->sk_type;
break;
case SO_PROTOCOL:
v.val = sk->sk_protocol;
break;
case SO_DOMAIN:
v.val = sk->sk_family;
break;
case SO_ERROR:
v.val = -sock_error(sk);
if (v.val == 0)
v.val = xchg(&sk->sk_err_soft, 0);
break;
case SO_OOBINLINE:
v.val = sock_flag(sk, SOCK_URGINLINE);
break;
case SO_NO_CHECK:
v.val = sk->sk_no_check_tx;
break;
case SO_PRIORITY:
v.val = sk->sk_priority;
break;
case SO_LINGER:
lv = sizeof(v.ling);
v.ling.l_onoff = sock_flag(sk, SOCK_LINGER);
v.ling.l_linger = sk->sk_lingertime / HZ;
break;
case SO_BSDCOMPAT:
sock_warn_obsolete_bsdism("getsockopt");
break;
case SO_TIMESTAMP:
v.val = sock_flag(sk, SOCK_RCVTSTAMP) &&
!sock_flag(sk, SOCK_RCVTSTAMPNS);
break;
case SO_TIMESTAMPNS:
v.val = sock_flag(sk, SOCK_RCVTSTAMPNS);
break;
case SO_TIMESTAMPING:
v.val = sk->sk_tsflags;
break;
case SO_RCVTIMEO:
lv = sizeof(struct timeval);
if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) {
v.tm.tv_sec = 0;
v.tm.tv_usec = 0;
} else {
v.tm.tv_sec = sk->sk_rcvtimeo / HZ;
v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * 1000000) / HZ;
}
break;
case SO_SNDTIMEO:
lv = sizeof(struct timeval);
if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) {
v.tm.tv_sec = 0;
v.tm.tv_usec = 0;
} else {
v.tm.tv_sec = sk->sk_sndtimeo / HZ;
v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * 1000000) / HZ;
}
break;
case SO_RCVLOWAT:
v.val = sk->sk_rcvlowat;
break;
case SO_SNDLOWAT:
v.val = 1;
break;
case SO_PASSCRED:
v.val = !!test_bit(SOCK_PASSCRED, &sock->flags);
break;
case SO_PEERCRED:
{
struct ucred peercred;
if (len > sizeof(peercred))
len = sizeof(peercred);
cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred);
if (copy_to_user(optval, &peercred, len))
return -EFAULT;
goto lenout;
}
case SO_PEERNAME:
{
char address[128];
if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2))
return -ENOTCONN;
if (lv < len)
return -EINVAL;
if (copy_to_user(optval, address, len))
return -EFAULT;
goto lenout;
}
/* Dubious BSD thing... Probably nobody even uses it, but
* the UNIX standard wants it for whatever reason... -DaveM
*/
case SO_ACCEPTCONN:
v.val = sk->sk_state == TCP_LISTEN;
break;
case SO_PASSSEC:
v.val = !!test_bit(SOCK_PASSSEC, &sock->flags);
break;
[AF_UNIX]: Datagram getpeersec This patch implements an API whereby an application can determine the label of its peer's Unix datagram sockets via the auxiliary data mechanism of recvmsg. Patch purpose: This patch enables a security-aware application to retrieve the security context of the peer of a Unix datagram socket. The application can then use this security context to determine the security context for processing on behalf of the peer who sent the packet. Patch design and implementation: The design and implementation is very similar to the UDP case for INET sockets. Basically we build upon the existing Unix domain socket API for retrieving user credentials. Linux offers the API for obtaining user credentials via ancillary messages (i.e., out of band/control messages that are bundled together with a normal message). To retrieve the security context, the application first indicates to the kernel such desire by setting the SO_PASSSEC option via getsockopt. Then the application retrieves the security context using the auxiliary data mechanism. An example server application for Unix datagram socket should look like this: toggle = 1; toggle_len = sizeof(toggle); setsockopt(sockfd, SOL_SOCKET, SO_PASSSEC, &toggle, &toggle_len); recvmsg(sockfd, &msg_hdr, 0); if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) { cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr); if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) && cmsg_hdr->cmsg_level == SOL_SOCKET && cmsg_hdr->cmsg_type == SCM_SECURITY) { memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext)); } } sock_setsockopt is enhanced with a new socket option SOCK_PASSSEC to allow a server socket to receive security context of the peer. Testing: We have tested the patch by setting up Unix datagram client and server applications. We verified that the server can retrieve the security context using the auxiliary data mechanism of recvmsg. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Acked-by: Acked-by: James Morris <jmorris@namei.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-30 02:27:47 +07:00
case SO_PEERSEC:
return security_socket_getpeersec_stream(sock, optval, optlen, len);
case SO_MARK:
v.val = sk->sk_mark;
break;
net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-13 03:26:31 +07:00
case SO_RXQ_OVFL:
v.val = sock_flag(sk, SOCK_RXQ_OVFL);
net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-13 03:26:31 +07:00
break;
case SO_WIFI_STATUS:
v.val = sock_flag(sk, SOCK_WIFI_STATUS);
break;
case SO_PEEK_OFF:
if (!sock->ops->set_peek_off)
return -EOPNOTSUPP;
v.val = sk->sk_peek_off;
break;
case SO_NOFCS:
v.val = sock_flag(sk, SOCK_NOFCS);
break;
case SO_BINDTODEVICE:
return sock_getbindtodevice(sk, optval, optlen, len);
sk-filter: Add ability to get socket filter program (v2) The SO_ATTACH_FILTER option is set only. I propose to add the get ability by using SO_ATTACH_FILTER in getsockopt. To be less irritating to eyes the SO_GET_FILTER alias to it is declared. This ability is required by checkpoint-restore project to be able to save full state of a socket. There are two issues with getting filter back. First, kernel modifies the sock_filter->code on filter load, thus in order to return the filter element back to user we have to decode it into user-visible constants. Fortunately the modification in question is interconvertible. Second, the BPF_S_ALU_DIV_K code modifies the command argument k to speed up the run-time division by doing kernel_k = reciprocal(user_k). Bad news is that different user_k may result in same kernel_k, so we can't get the original user_k back. Good news is that we don't have to do it. What we need to is calculate a user2_k so, that reciprocal(user2_k) == reciprocal(user_k) == kernel_k i.e. if it's re-loaded back the compiled again value will be exactly the same as it was. That said, the user2_k can be calculated like this user2_k = reciprocal(kernel_k) with an exception, that if kernel_k == 0, then user2_k == 1. The optlen argument is treated like this -- when zero, kernel returns the amount of sock_fprog elements in filter, otherwise it should be large enough for the sock_fprog array. changes since v1: * Declared SO_GET_FILTER in all arch headers * Added decode of vlan-tag codes Signed-off-by: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-01 09:01:48 +07:00
case SO_GET_FILTER:
len = sk_get_filter(sk, (struct sock_filter __user *)optval, len);
if (len < 0)
return len;
goto lenout;
case SO_LOCK_FILTER:
v.val = sock_flag(sk, SOCK_FILTER_LOCKED);
break;
case SO_BPF_EXTENSIONS:
v.val = bpf_tell_extensions();
break;
case SO_SELECT_ERR_QUEUE:
v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE);
break;
#ifdef CONFIG_NET_RX_BUSY_POLL
case SO_BUSY_POLL:
v.val = sk->sk_ll_usec;
break;
#endif
case SO_MAX_PACING_RATE:
v.val = sk->sk_max_pacing_rate;
break;
case SO_INCOMING_CPU:
v.val = sk->sk_incoming_cpu;
break;
default:
/* We implement the SO_SNDLOWAT etc to not be settable
* (1003.1g 7).
*/
return -ENOPROTOOPT;
}
if (len > lv)
len = lv;
if (copy_to_user(optval, &v, len))
return -EFAULT;
lenout:
if (put_user(len, optlen))
return -EFAULT;
return 0;
}
/*
* Initialize an sk_lock.
*
* (We also register the sk_lock with the lock validator.)
*/
static inline void sock_lock_init(struct sock *sk)
{
sock_lock_init_class_and_name(sk,
af_family_slock_key_strings[sk->sk_family],
af_family_slock_keys + sk->sk_family,
af_family_key_strings[sk->sk_family],
af_family_keys + sk->sk_family);
}
/*
* Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet,
* even temporarly, because of RCU lookups. sk_node should also be left as is.
* We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end
*/
static void sock_copy(struct sock *nsk, const struct sock *osk)
{
#ifdef CONFIG_SECURITY_NETWORK
void *sptr = nsk->sk_security;
#endif
memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin));
memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end,
osk->sk_prot->obj_size - offsetof(struct sock, sk_dontcopy_end));
#ifdef CONFIG_SECURITY_NETWORK
nsk->sk_security = sptr;
security_sk_clone(osk, nsk);
#endif
}
void sk_prot_clear_portaddr_nulls(struct sock *sk, int size)
{
unsigned long nulls1, nulls2;
nulls1 = offsetof(struct sock, __sk_common.skc_node.next);
nulls2 = offsetof(struct sock, __sk_common.skc_portaddr_node.next);
if (nulls1 > nulls2)
swap(nulls1, nulls2);
if (nulls1 != 0)
memset((char *)sk, 0, nulls1);
memset((char *)sk + nulls1 + sizeof(void *), 0,
nulls2 - nulls1 - sizeof(void *));
memset((char *)sk + nulls2 + sizeof(void *), 0,
size - nulls2 - sizeof(void *));
}
EXPORT_SYMBOL(sk_prot_clear_portaddr_nulls);
static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
int family)
{
struct sock *sk;
struct kmem_cache *slab;
slab = prot->slab;
if (slab != NULL) {
sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO);
if (!sk)
return sk;
if (priority & __GFP_ZERO) {
if (prot->clear_sk)
prot->clear_sk(sk, prot->obj_size);
else
sk_prot_clear_nulls(sk, prot->obj_size);
}
} else
sk = kmalloc(prot->obj_size, priority);
if (sk != NULL) {
net: annotate struct sock bitfield 2009/2/24 Ingo Molnar <mingo@elte.hu>: > ok, this is the last warning i have from today's overnight -tip > testruns - a 32-bit system warning in sock_init_data(): > > [ 2.610389] NET: Registered protocol family 16 > [ 2.616138] initcall netlink_proto_init+0x0/0x170 returned 0 after 7812 usecs > [ 2.620010] WARNING: kmemcheck: Caught 32-bit read from uninitialized memory (f642c184) > [ 2.624002] 010000000200000000000000604990c000000000000000000000000000000000 > [ 2.634076] i i i i i i u u i i i i i i i i i i i i i i i i i i i i i i i i > [ 2.641038] ^ > [ 2.643376] > [ 2.644004] Pid: 1, comm: swapper Not tainted (2.6.29-rc6-tip-01751-g4d1c22c-dirty #885) > [ 2.648003] EIP: 0060:[<c07141a1>] EFLAGS: 00010282 CPU: 0 > [ 2.652008] EIP is at sock_init_data+0xa1/0x190 > [ 2.656003] EAX: 0001a800 EBX: f6836c00 ECX: 00463000 EDX: c0e46fe0 > [ 2.660003] ESI: f642c180 EDI: c0b83088 EBP: f6863ed8 ESP: c0c412ec > [ 2.664003] DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 > [ 2.668003] CR0: 8005003b CR2: f682c400 CR3: 00b91000 CR4: 000006f0 > [ 2.672003] DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 > [ 2.676003] DR6: ffff4ff0 DR7: 00000400 > [ 2.680002] [<c07423e5>] __netlink_create+0x35/0xa0 > [ 2.684002] [<c07443cc>] netlink_kernel_create+0x4c/0x140 > [ 2.688002] [<c072755e>] rtnetlink_net_init+0x1e/0x40 > [ 2.696002] [<c071b601>] register_pernet_operations+0x11/0x30 > [ 2.700002] [<c071b72c>] register_pernet_subsys+0x1c/0x30 > [ 2.704002] [<c0bf3c8c>] rtnetlink_init+0x4c/0x100 > [ 2.708002] [<c0bf4669>] netlink_proto_init+0x159/0x170 > [ 2.712002] [<c0101124>] do_one_initcall+0x24/0x150 > [ 2.716002] [<c0bbf3c7>] do_initcalls+0x27/0x40 > [ 2.723201] [<c0bbf3fc>] do_basic_setup+0x1c/0x20 > [ 2.728002] [<c0bbfb8a>] kernel_init+0x5a/0xa0 > [ 2.732002] [<c0103e47>] kernel_thread_helper+0x7/0x10 > [ 2.736002] [<ffffffff>] 0xffffffff We fix this false positive by annotating the bitfield in struct sock. Reported-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
2009-02-26 20:46:57 +07:00
kmemcheck_annotate_bitfield(sk, flags);
if (security_sk_alloc(sk, family, priority))
goto out_free;
if (!try_module_get(prot->owner))
goto out_free_sec;
sk_tx_queue_clear(sk);
}
return sk;
out_free_sec:
security_sk_free(sk);
out_free:
if (slab != NULL)
kmem_cache_free(slab, sk);
else
kfree(sk);
return NULL;
}
static void sk_prot_free(struct proto *prot, struct sock *sk)
{
struct kmem_cache *slab;
struct module *owner;
owner = prot->owner;
slab = prot->slab;
security_sk_free(sk);
if (slab != NULL)
kmem_cache_free(slab, sk);
else
kfree(sk);
module_put(owner);
}
#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
void sock_update_netprioidx(struct sock *sk)
{
if (in_interrupt())
return;
sk->sk_cgrp_prioidx = task_netprioidx(current);
}
EXPORT_SYMBOL_GPL(sock_update_netprioidx);
cls_cgroup: Store classid in struct sock Up until now cls_cgroup has relied on fetching the classid out of the current executing thread. This runs into trouble when a packet processing is delayed in which case it may execute out of another thread's context. Furthermore, even when a packet is not delayed we may fail to classify it if soft IRQs have been disabled, because this scenario is indistinguishable from one where a packet unrelated to the current thread is processed by a real soft IRQ. In fact, the current semantics is inherently broken, as a single skb may be constructed out of the writes of two different tasks. A different manifestation of this problem is when the TCP stack transmits in response of an incoming ACK. This is currently unclassified. As we already have a concept of packet ownership for accounting purposes in the skb->sk pointer, this is a natural place to store the classid in a persistent manner. This patch adds the cls_cgroup classid in struct sock, filling up an existing hole on 64-bit :) The value is set at socket creation time. So all sockets created via socket(2) automatically gains the ID of the thread creating it. Whenever another process touches the socket by either reading or writing to it, we will change the socket classid to that of the process if it has a valid (non-zero) classid. For sockets created on inbound connections through accept(2), we inherit the classid of the original listening socket through sk_clone, possibly preceding the actual accept(2) call. In order to minimise risks, I have not made this the authoritative classid. For now it is only used as a backup when we execute with soft IRQs disabled. Once we're completely happy with its semantics we can use it as the sole classid. Footnote: I have rearranged the error path on cls_group module creation. If we didn't do this, then there is a window where someone could create a tc rule using cls_group before the cgroup subsystem has been registered. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-24 14:12:34 +07:00
#endif
/**
* sk_alloc - All socket objects are allocated here
* @net: the applicable net namespace
[PATCH] DocBook: changes and extensions to the kernel documentation I have recompiled Linux kernel 2.6.11.5 documentation for me and our university students again. The documentation could be extended for more sources which are equipped by structured comments for recent 2.6 kernels. I have tried to proceed with that task. I have done that more times from 2.6.0 time and it gets boring to do same changes again and again. Linux kernel compiles after changes for i386 and ARM targets. I have added references to some more files into kernel-api book, I have added some section names as well. So please, check that changes do not break something and that categories are not too much skewed. I have changed kernel-doc to accept "fastcall" and "asmlinkage" words reserved by kernel convention. Most of the other changes are modifications in the comments to make kernel-doc happy, accept some parameters description and do not bail out on errors. Changed <pid> to @pid in the description, moved some #ifdef before comments to correct function to comments bindings, etc. You can see result of the modified documentation build at http://cmp.felk.cvut.cz/~pisa/linux/lkdb-2.6.11.tar.gz Some more sources are ready to be included into kernel-doc generated documentation. Sources has been added into kernel-api for now. Some more section names added and probably some more chaos introduced as result of quick cleanup work. Signed-off-by: Pavel Pisa <pisa@cmp.felk.cvut.cz> Signed-off-by: Martin Waitz <tali@admingilde.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 22:59:25 +07:00
* @family: protocol family
* @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
* @prot: struct proto associated with this new sock instance
* @kern: is this to be a kernel socket?
*/
struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
struct proto *prot, int kern)
{
struct sock *sk;
sk = sk_prot_alloc(prot, priority | __GFP_ZERO, family);
if (sk) {
sk->sk_family = family;
/*
* See comment in struct sock definition to understand
* why we need sk_prot_creator -acme
*/
sk->sk_prot = sk->sk_prot_creator = prot;
sock_lock_init(sk);
sk->sk_net_refcnt = kern ? 0 : 1;
if (likely(sk->sk_net_refcnt))
get_net(net);
sock_net_set(sk, net);
atomic_set(&sk->sk_wmem_alloc, 1);
cls_cgroup: Store classid in struct sock Up until now cls_cgroup has relied on fetching the classid out of the current executing thread. This runs into trouble when a packet processing is delayed in which case it may execute out of another thread's context. Furthermore, even when a packet is not delayed we may fail to classify it if soft IRQs have been disabled, because this scenario is indistinguishable from one where a packet unrelated to the current thread is processed by a real soft IRQ. In fact, the current semantics is inherently broken, as a single skb may be constructed out of the writes of two different tasks. A different manifestation of this problem is when the TCP stack transmits in response of an incoming ACK. This is currently unclassified. As we already have a concept of packet ownership for accounting purposes in the skb->sk pointer, this is a natural place to store the classid in a persistent manner. This patch adds the cls_cgroup classid in struct sock, filling up an existing hole on 64-bit :) The value is set at socket creation time. So all sockets created via socket(2) automatically gains the ID of the thread creating it. Whenever another process touches the socket by either reading or writing to it, we will change the socket classid to that of the process if it has a valid (non-zero) classid. For sockets created on inbound connections through accept(2), we inherit the classid of the original listening socket through sk_clone, possibly preceding the actual accept(2) call. In order to minimise risks, I have not made this the authoritative classid. For now it is only used as a backup when we execute with soft IRQs disabled. Once we're completely happy with its semantics we can use it as the sole classid. Footnote: I have rearranged the error path on cls_group module creation. If we didn't do this, then there is a window where someone could create a tc rule using cls_group before the cgroup subsystem has been registered. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-24 14:12:34 +07:00
sock_update_classid(sk);
sock_update_netprioidx(sk);
}
[NET]: Fix module reference counts for loadable protocol modules I have been experimenting with loadable protocol modules, and ran into several issues with module reference counting. The first issue was that __module_get failed at the BUG_ON check at the top of the routine (checking that my module reference count was not zero) when I created the first socket. When sk_alloc() is called, my module reference count was still 0. When I looked at why sctp didn't have this problem, I discovered that sctp creates a control socket during module init (when the module ref count is not 0), which keeps the reference count non-zero. This section has been updated to address the point Stephen raised about checking the return value of try_module_get(). The next problem arose when my socket init routine returned an error. This resulted in my module reference count being decremented below 0. My socket ops->release routine was also being called. The issue here is that sock_release() calls the ops->release routine and decrements the ref count if sock->ops is not NULL. Since the socket probably didn't get correctly initialized, this should not be done, so we will set sock->ops to NULL because we will not call try_module_get(). While searching for another bug, I also noticed that sys_accept() has a possibility of doing a module_put() when it did not do an __module_get so I re-ordered the call to security_socket_accept(). Signed-off-by: Frank Filz <ffilzlnx@us.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-28 05:23:38 +07:00
return sk;
}
EXPORT_SYMBOL(sk_alloc);
void sk_destruct(struct sock *sk)
{
struct sk_filter *filter;
if (sk->sk_destruct)
sk->sk_destruct(sk);
filter = rcu_dereference_check(sk->sk_filter,
atomic_read(&sk->sk_wmem_alloc) == 0);
if (filter) {
sk_filter_uncharge(sk, filter);
RCU_INIT_POINTER(sk->sk_filter, NULL);
}
sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP);
if (atomic_read(&sk->sk_omem_alloc))
pr_debug("%s: optmem leakage (%d bytes) detected\n",
__func__, atomic_read(&sk->sk_omem_alloc));
if (sk->sk_peer_cred)
put_cred(sk->sk_peer_cred);
put_pid(sk->sk_peer_pid);
if (likely(sk->sk_net_refcnt))
put_net(sock_net(sk));
sk_prot_free(sk->sk_prot_creator, sk);
}
net: No more expensive sock_hold()/sock_put() on each tx One of the problem with sock memory accounting is it uses a pair of sock_hold()/sock_put() for each transmitted packet. This slows down bidirectional flows because the receive path also needs to take a refcount on socket and might use a different cpu than transmit path or transmit completion path. So these two atomic operations also trigger cache line bounces. We can see this in tx or tx/rx workloads (media gateways for example), where sock_wfree() can be in top five functions in profiles. We use this sock_hold()/sock_put() so that sock freeing is delayed until all tx packets are completed. As we also update sk_wmem_alloc, we could offset sk_wmem_alloc by one unit at init time, until sk_free() is called. Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc) to decrement initial offset and atomicaly check if any packets are in flight. skb_set_owner_w() doesnt call sock_hold() anymore sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc reached 0 to perform the final freeing. Drawback is that a skb->truesize error could lead to unfreeable sockets, or even worse, prematurely calling __sk_free() on a live socket. Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt contention point. 5 % speedup on a UDP transmit workload (depends on number of flows), lowering TX completion cpu usage. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 16:55:43 +07:00
static void __sk_free(struct sock *sk)
{
sock_diag: don't broadcast kernel sockets Kernel sockets do not hold a reference for the network namespace to which they point. Socket destruction broadcasting relies on the network namespace and will cause the splat below when a kernel socket is destroyed. This fix simply ignores kernel sockets when they are destroyed. Reported as: general protection fault: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC CPU: 1 PID: 9130 Comm: kworker/1:1 Not tainted 4.1.0-gelk-debug+ #1 Workqueue: sock_diag_events sock_diag_broadcast_destroy_work Stack: ffff8800b9c586c0 ffff8800b9c586c0 ffff8800ac4692c0 ffff8800936d4a90 ffff8800352efd38 ffffffff8469a93e ffff8800352efd98 ffffffffc09b9b90 ffff8800352efd78 ffff8800ac4692c0 ffff8800b9c586c0 ffff8800831b6ab8 Call Trace: [<ffffffff8469a93e>] ? mutex_unlock+0xe/0x10 [<ffffffffc09b9b90>] ? inet_diag_handler_get_info+0x110/0x1fb [inet_diag] [<ffffffff845c868d>] netlink_broadcast+0x1d/0x20 [<ffffffff8469a93e>] ? mutex_unlock+0xe/0x10 [<ffffffff845b2bf5>] sock_diag_broadcast_destroy_work+0xd5/0x160 [<ffffffff8408ea97>] process_one_work+0x147/0x420 [<ffffffff8408f0f9>] worker_thread+0x69/0x470 [<ffffffff8409fda3>] ? preempt_count_sub+0xa3/0xf0 [<ffffffff8408f090>] ? rescuer_thread+0x320/0x320 [<ffffffff84093cd7>] kthread+0x107/0x120 [<ffffffff84093bd0>] ? kthread_create_on_node+0x1b0/0x1b0 [<ffffffff8469d31f>] ret_from_fork+0x3f/0x70 [<ffffffff84093bd0>] ? kthread_create_on_node+0x1b0/0x1b0 Tested: Using a debug kernel while 'ss -E' is running: ip netns add test-ns ip netns delete test-ns Fixes: eb4cb008529c sock_diag: define destruction multicast groups Fixes: 26abe14379f8 net: Modify sk_alloc to not reference count the netns of kernel sockets. Reported-by: Dave Jones <davej@codemonkey.org.uk> Suggested-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Craig Gallek <kraig@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-30 23:49:32 +07:00
if (unlikely(sock_diag_has_destroy_listeners(sk) && sk->sk_net_refcnt))
sock_diag_broadcast_destroy(sk);
else
sk_destruct(sk);
}
net: No more expensive sock_hold()/sock_put() on each tx One of the problem with sock memory accounting is it uses a pair of sock_hold()/sock_put() for each transmitted packet. This slows down bidirectional flows because the receive path also needs to take a refcount on socket and might use a different cpu than transmit path or transmit completion path. So these two atomic operations also trigger cache line bounces. We can see this in tx or tx/rx workloads (media gateways for example), where sock_wfree() can be in top five functions in profiles. We use this sock_hold()/sock_put() so that sock freeing is delayed until all tx packets are completed. As we also update sk_wmem_alloc, we could offset sk_wmem_alloc by one unit at init time, until sk_free() is called. Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc) to decrement initial offset and atomicaly check if any packets are in flight. skb_set_owner_w() doesnt call sock_hold() anymore sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc reached 0 to perform the final freeing. Drawback is that a skb->truesize error could lead to unfreeable sockets, or even worse, prematurely calling __sk_free() on a live socket. Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt contention point. 5 % speedup on a UDP transmit workload (depends on number of flows), lowering TX completion cpu usage. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 16:55:43 +07:00
void sk_free(struct sock *sk)
{
/*
* We subtract one from sk_wmem_alloc and can know if
net: No more expensive sock_hold()/sock_put() on each tx One of the problem with sock memory accounting is it uses a pair of sock_hold()/sock_put() for each transmitted packet. This slows down bidirectional flows because the receive path also needs to take a refcount on socket and might use a different cpu than transmit path or transmit completion path. So these two atomic operations also trigger cache line bounces. We can see this in tx or tx/rx workloads (media gateways for example), where sock_wfree() can be in top five functions in profiles. We use this sock_hold()/sock_put() so that sock freeing is delayed until all tx packets are completed. As we also update sk_wmem_alloc, we could offset sk_wmem_alloc by one unit at init time, until sk_free() is called. Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc) to decrement initial offset and atomicaly check if any packets are in flight. skb_set_owner_w() doesnt call sock_hold() anymore sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc reached 0 to perform the final freeing. Drawback is that a skb->truesize error could lead to unfreeable sockets, or even worse, prematurely calling __sk_free() on a live socket. Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt contention point. 5 % speedup on a UDP transmit workload (depends on number of flows), lowering TX completion cpu usage. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 16:55:43 +07:00
* some packets are still in some tx queue.
* If not null, sock_wfree() will call __sk_free(sk) later
*/
if (atomic_dec_and_test(&sk->sk_wmem_alloc))
__sk_free(sk);
}
EXPORT_SYMBOL(sk_free);
static void sk_update_clone(const struct sock *sk, struct sock *newsk)
{
if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
sock_update_memcg(newsk);
}
/**
* sk_clone_lock - clone a socket, and lock its clone
* @sk: the socket to clone
* @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
*
* Caller must unlock socket even in error path (bh_unlock_sock(newsk))
*/
struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
{
struct sock *newsk;
bool is_charged = true;
newsk = sk_prot_alloc(sk->sk_prot, priority, sk->sk_family);
if (newsk != NULL) {
struct sk_filter *filter;
sock_copy(newsk, sk);
/* SANITY */
if (likely(newsk->sk_net_refcnt))
get_net(sock_net(newsk));
sk_node_init(&newsk->sk_node);
sock_lock_init(newsk);
bh_lock_sock(newsk);
newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL;
net: add limit for socket backlog We got system OOM while running some UDP netperf testing on the loopback device. The case is multiple senders sent stream UDP packets to a single receiver via loopback on local host. Of course, the receiver is not able to handle all the packets in time. But we surprisingly found that these packets were not discarded due to the receiver's sk->sk_rcvbuf limit. Instead, they are kept queuing to sk->sk_backlog and finally ate up all the memory. We believe this is a secure hole that a none privileged user can crash the system. The root cause for this problem is, when the receiver is doing __release_sock() (i.e. after userspace recv, kernel udp_recvmsg -> skb_free_datagram_locked -> release_sock), it moves skbs from backlog to sk_receive_queue with the softirq enabled. In the above case, multiple busy senders will almost make it an endless loop. The skbs in the backlog end up eat all the system memory. The issue is not only for UDP. Any protocols using socket backlog is potentially affected. The patch adds limit for socket backlog so that the backlog size cannot be expanded endlessly. Reported-by: Alex Shi <alex.shi@intel.com> Cc: David Miller <davem@davemloft.net> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru Cc: "Pekka Savola (ipv6)" <pekkas@netcore.fi> Cc: Patrick McHardy <kaber@trash.net> Cc: Vlad Yasevich <vladislav.yasevich@hp.com> Cc: Sridhar Samudrala <sri@us.ibm.com> Cc: Jon Maloy <jon.maloy@ericsson.com> Cc: Allan Stephens <allan.stephens@windriver.com> Cc: Andrew Hendry <andrew.hendry@gmail.com> Signed-off-by: Zhu Yi <yi.zhu@intel.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-03-05 01:01:40 +07:00
newsk->sk_backlog.len = 0;
atomic_set(&newsk->sk_rmem_alloc, 0);
net: No more expensive sock_hold()/sock_put() on each tx One of the problem with sock memory accounting is it uses a pair of sock_hold()/sock_put() for each transmitted packet. This slows down bidirectional flows because the receive path also needs to take a refcount on socket and might use a different cpu than transmit path or transmit completion path. So these two atomic operations also trigger cache line bounces. We can see this in tx or tx/rx workloads (media gateways for example), where sock_wfree() can be in top five functions in profiles. We use this sock_hold()/sock_put() so that sock freeing is delayed until all tx packets are completed. As we also update sk_wmem_alloc, we could offset sk_wmem_alloc by one unit at init time, until sk_free() is called. Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc) to decrement initial offset and atomicaly check if any packets are in flight. skb_set_owner_w() doesnt call sock_hold() anymore sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc reached 0 to perform the final freeing. Drawback is that a skb->truesize error could lead to unfreeable sockets, or even worse, prematurely calling __sk_free() on a live socket. Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt contention point. 5 % speedup on a UDP transmit workload (depends on number of flows), lowering TX completion cpu usage. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 16:55:43 +07:00
/*
* sk_wmem_alloc set to one (see sk_free() and sock_wfree())
*/
atomic_set(&newsk->sk_wmem_alloc, 1);
atomic_set(&newsk->sk_omem_alloc, 0);
skb_queue_head_init(&newsk->sk_receive_queue);
skb_queue_head_init(&newsk->sk_write_queue);
spin_lock_init(&newsk->sk_dst_lock);
rwlock_init(&newsk->sk_callback_lock);
lockdep_set_class_and_name(&newsk->sk_callback_lock,
af_callback_keys + newsk->sk_family,
af_family_clock_key_strings[newsk->sk_family]);
newsk->sk_dst_cache = NULL;
newsk->sk_wmem_queued = 0;
newsk->sk_forward_alloc = 0;
newsk->sk_send_head = NULL;
newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
sock_reset_flag(newsk, SOCK_DONE);
skb_queue_head_init(&newsk->sk_error_queue);
filter = rcu_dereference_protected(newsk->sk_filter, 1);
if (filter != NULL)
/* though it's an empty new sock, the charging may fail
* if sysctl_optmem_max was changed between creation of
* original socket and cloning
*/
is_charged = sk_filter_charge(newsk, filter);
if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk))) {
/* It is still raw copy of parent, so invalidate
* destructor and make plain sk_free() */
newsk->sk_destruct = NULL;
bh_unlock_sock(newsk);
sk_free(newsk);
newsk = NULL;
goto out;
}
newsk->sk_err = 0;
newsk->sk_priority = 0;
newsk->sk_incoming_cpu = raw_smp_processor_id();
atomic64_set(&newsk->sk_cookie, 0);
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
*/
smp_wmb();
atomic_set(&newsk->sk_refcnt, 2);
/*
* Increment the counter in the same struct proto as the master
* sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that
* is the same as sk->sk_prot->socks, as this field was copied
* with memcpy).
*
* This _changes_ the previous behaviour, where
* tcp_create_openreq_child always was incrementing the
* equivalent to tcp_prot->socks (inet_sock_nr), so this have
* to be taken into account in all callers. -acme
*/
sk_refcnt_debug_inc(newsk);
sk_set_socket(newsk, NULL);
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 18:01:49 +07:00
newsk->sk_wq = NULL;
sk_update_clone(sk, newsk);
if (newsk->sk_prot->sockets_allocated)
sk_sockets_allocated_inc(newsk);
if (newsk->sk_flags & SK_FLAGS_TIMESTAMP)
net_enable_timestamp();
}
out:
return newsk;
}
EXPORT_SYMBOL_GPL(sk_clone_lock);
void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
{
u32 max_segs = 1;
__sk_dst_set(sk, dst);
sk->sk_route_caps = dst->dev->features;
if (sk->sk_route_caps & NETIF_F_GSO)
sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
sk->sk_route_caps &= ~sk->sk_route_nocaps;
if (sk_can_gso(sk)) {
[NET]: Add per-connection option to set max TSO frame size Update: My mailer ate one of Jarek's feedback mails... Fixed the parameter in netif_set_gso_max_size() to be u32, not u16. Fixed the whitespace issue due to a patch import botch. Changed the types from u32 to unsigned int to be more consistent with other variables in the area. Also brought the patch up to the latest net-2.6.26 tree. Update: Made gso_max_size container 32 bits, not 16. Moved the location of gso_max_size within netdev to be less hotpath. Made more consistent names between the sock and netdev layers, and added a define for the max GSO size. Update: Respun for net-2.6.26 tree. Update: changed max_gso_frame_size and sk_gso_max_size from signed to unsigned - thanks Stephen! This patch adds the ability for device drivers to control the size of the TSO frames being sent to them, per TCP connection. By setting the netdevice's gso_max_size value, the socket layer will set the GSO frame size based on that value. This will propogate into the TCP layer, and send TSO's of that size to the hardware. This can be desirable to help tune the bursty nature of TSO on a per-adapter basis, where one may have 1 GbE and 10 GbE devices coexisting in a system, one running multiqueue and the other not, etc. This can also be desirable for devices that cannot support full 64 KB TSO's, but still want to benefit from some level of segmentation offloading. Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-21 17:43:19 +07:00
if (dst->header_len) {
sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
[NET]: Add per-connection option to set max TSO frame size Update: My mailer ate one of Jarek's feedback mails... Fixed the parameter in netif_set_gso_max_size() to be u32, not u16. Fixed the whitespace issue due to a patch import botch. Changed the types from u32 to unsigned int to be more consistent with other variables in the area. Also brought the patch up to the latest net-2.6.26 tree. Update: Made gso_max_size container 32 bits, not 16. Moved the location of gso_max_size within netdev to be less hotpath. Made more consistent names between the sock and netdev layers, and added a define for the max GSO size. Update: Respun for net-2.6.26 tree. Update: changed max_gso_frame_size and sk_gso_max_size from signed to unsigned - thanks Stephen! This patch adds the ability for device drivers to control the size of the TSO frames being sent to them, per TCP connection. By setting the netdevice's gso_max_size value, the socket layer will set the GSO frame size based on that value. This will propogate into the TCP layer, and send TSO's of that size to the hardware. This can be desirable to help tune the bursty nature of TSO on a per-adapter basis, where one may have 1 GbE and 10 GbE devices coexisting in a system, one running multiqueue and the other not, etc. This can also be desirable for devices that cannot support full 64 KB TSO's, but still want to benefit from some level of segmentation offloading. Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-21 17:43:19 +07:00
} else {
sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
[NET]: Add per-connection option to set max TSO frame size Update: My mailer ate one of Jarek's feedback mails... Fixed the parameter in netif_set_gso_max_size() to be u32, not u16. Fixed the whitespace issue due to a patch import botch. Changed the types from u32 to unsigned int to be more consistent with other variables in the area. Also brought the patch up to the latest net-2.6.26 tree. Update: Made gso_max_size container 32 bits, not 16. Moved the location of gso_max_size within netdev to be less hotpath. Made more consistent names between the sock and netdev layers, and added a define for the max GSO size. Update: Respun for net-2.6.26 tree. Update: changed max_gso_frame_size and sk_gso_max_size from signed to unsigned - thanks Stephen! This patch adds the ability for device drivers to control the size of the TSO frames being sent to them, per TCP connection. By setting the netdevice's gso_max_size value, the socket layer will set the GSO frame size based on that value. This will propogate into the TCP layer, and send TSO's of that size to the hardware. This can be desirable to help tune the bursty nature of TSO on a per-adapter basis, where one may have 1 GbE and 10 GbE devices coexisting in a system, one running multiqueue and the other not, etc. This can also be desirable for devices that cannot support full 64 KB TSO's, but still want to benefit from some level of segmentation offloading. Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-21 17:43:19 +07:00
sk->sk_gso_max_size = dst->dev->gso_max_size;
max_segs = max_t(u32, dst->dev->gso_max_segs, 1);
[NET]: Add per-connection option to set max TSO frame size Update: My mailer ate one of Jarek's feedback mails... Fixed the parameter in netif_set_gso_max_size() to be u32, not u16. Fixed the whitespace issue due to a patch import botch. Changed the types from u32 to unsigned int to be more consistent with other variables in the area. Also brought the patch up to the latest net-2.6.26 tree. Update: Made gso_max_size container 32 bits, not 16. Moved the location of gso_max_size within netdev to be less hotpath. Made more consistent names between the sock and netdev layers, and added a define for the max GSO size. Update: Respun for net-2.6.26 tree. Update: changed max_gso_frame_size and sk_gso_max_size from signed to unsigned - thanks Stephen! This patch adds the ability for device drivers to control the size of the TSO frames being sent to them, per TCP connection. By setting the netdevice's gso_max_size value, the socket layer will set the GSO frame size based on that value. This will propogate into the TCP layer, and send TSO's of that size to the hardware. This can be desirable to help tune the bursty nature of TSO on a per-adapter basis, where one may have 1 GbE and 10 GbE devices coexisting in a system, one running multiqueue and the other not, etc. This can also be desirable for devices that cannot support full 64 KB TSO's, but still want to benefit from some level of segmentation offloading. Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-21 17:43:19 +07:00
}
}
sk->sk_gso_max_segs = max_segs;
}
EXPORT_SYMBOL_GPL(sk_setup_caps);
/*
* Simple resource managers for sockets.
*/
/*
* Write buffer destructor automatically called from kfree_skb.
*/
void sock_wfree(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
unsigned int len = skb->truesize;
if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) {
/*
* Keep a reference on sk_wmem_alloc, this will be released
* after sk_write_space() call
*/
atomic_sub(len - 1, &sk->sk_wmem_alloc);
sk->sk_write_space(sk);
len = 1;
}
net: No more expensive sock_hold()/sock_put() on each tx One of the problem with sock memory accounting is it uses a pair of sock_hold()/sock_put() for each transmitted packet. This slows down bidirectional flows because the receive path also needs to take a refcount on socket and might use a different cpu than transmit path or transmit completion path. So these two atomic operations also trigger cache line bounces. We can see this in tx or tx/rx workloads (media gateways for example), where sock_wfree() can be in top five functions in profiles. We use this sock_hold()/sock_put() so that sock freeing is delayed until all tx packets are completed. As we also update sk_wmem_alloc, we could offset sk_wmem_alloc by one unit at init time, until sk_free() is called. Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc) to decrement initial offset and atomicaly check if any packets are in flight. skb_set_owner_w() doesnt call sock_hold() anymore sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc reached 0 to perform the final freeing. Drawback is that a skb->truesize error could lead to unfreeable sockets, or even worse, prematurely calling __sk_free() on a live socket. Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt contention point. 5 % speedup on a UDP transmit workload (depends on number of flows), lowering TX completion cpu usage. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 16:55:43 +07:00
/*
* if sk_wmem_alloc reaches 0, we must finish what sk_free()
* could not do because of in-flight packets
net: No more expensive sock_hold()/sock_put() on each tx One of the problem with sock memory accounting is it uses a pair of sock_hold()/sock_put() for each transmitted packet. This slows down bidirectional flows because the receive path also needs to take a refcount on socket and might use a different cpu than transmit path or transmit completion path. So these two atomic operations also trigger cache line bounces. We can see this in tx or tx/rx workloads (media gateways for example), where sock_wfree() can be in top five functions in profiles. We use this sock_hold()/sock_put() so that sock freeing is delayed until all tx packets are completed. As we also update sk_wmem_alloc, we could offset sk_wmem_alloc by one unit at init time, until sk_free() is called. Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc) to decrement initial offset and atomicaly check if any packets are in flight. skb_set_owner_w() doesnt call sock_hold() anymore sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc reached 0 to perform the final freeing. Drawback is that a skb->truesize error could lead to unfreeable sockets, or even worse, prematurely calling __sk_free() on a live socket. Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt contention point. 5 % speedup on a UDP transmit workload (depends on number of flows), lowering TX completion cpu usage. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 16:55:43 +07:00
*/
if (atomic_sub_and_test(len, &sk->sk_wmem_alloc))
net: No more expensive sock_hold()/sock_put() on each tx One of the problem with sock memory accounting is it uses a pair of sock_hold()/sock_put() for each transmitted packet. This slows down bidirectional flows because the receive path also needs to take a refcount on socket and might use a different cpu than transmit path or transmit completion path. So these two atomic operations also trigger cache line bounces. We can see this in tx or tx/rx workloads (media gateways for example), where sock_wfree() can be in top five functions in profiles. We use this sock_hold()/sock_put() so that sock freeing is delayed until all tx packets are completed. As we also update sk_wmem_alloc, we could offset sk_wmem_alloc by one unit at init time, until sk_free() is called. Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc) to decrement initial offset and atomicaly check if any packets are in flight. skb_set_owner_w() doesnt call sock_hold() anymore sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc reached 0 to perform the final freeing. Drawback is that a skb->truesize error could lead to unfreeable sockets, or even worse, prematurely calling __sk_free() on a live socket. Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt contention point. 5 % speedup on a UDP transmit workload (depends on number of flows), lowering TX completion cpu usage. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 16:55:43 +07:00
__sk_free(sk);
}
EXPORT_SYMBOL(sock_wfree);
void skb_orphan_partial(struct sk_buff *skb)
{
/* TCP stack sets skb->ooo_okay based on sk_wmem_alloc,
* so we do not completely orphan skb, but transfert all
* accounted bytes but one, to avoid unexpected reorders.
*/
if (skb->destructor == sock_wfree
#ifdef CONFIG_INET
|| skb->destructor == tcp_wfree
#endif
) {
atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc);
skb->truesize = 1;
} else {
skb_orphan(skb);
}
}
EXPORT_SYMBOL(skb_orphan_partial);
/*
* Read buffer destructor automatically called from kfree_skb.
*/
void sock_rfree(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
unsigned int len = skb->truesize;
atomic_sub(len, &sk->sk_rmem_alloc);
sk_mem_uncharge(sk, len);
}
EXPORT_SYMBOL(sock_rfree);
/*
* Buffer destructor for skbs that are not used directly in read or write
* path, e.g. for error handler skbs. Automatically called from kfree_skb.
*/
void sock_efree(struct sk_buff *skb)
{
sock_put(skb->sk);
}
EXPORT_SYMBOL(sock_efree);
kuid_t sock_i_uid(struct sock *sk)
{
kuid_t uid;
net: fix a lockdep splat We have for each socket : One spinlock (sk_slock.slock) One rwlock (sk_callback_lock) Possible scenarios are : (A) (this is used in net/sunrpc/xprtsock.c) read_lock(&sk->sk_callback_lock) (without blocking BH) <BH> spin_lock(&sk->sk_slock.slock); ... read_lock(&sk->sk_callback_lock); ... (B) write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) (C) spin_lock_bh(&sk->sk_slock) ... write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) spin_unlock_bh(&sk->sk_slock) This (C) case conflicts with (A) : CPU1 [A] CPU2 [C] read_lock(callback_lock) <BH> spin_lock_bh(slock) <wait to spin_lock(slock)> <wait to write_lock_bh(callback_lock)> We have one problematic (C) use case in inet_csk_listen_stop() : local_bh_disable(); bh_lock_sock(child); // spin_lock_bh(&sk->sk_slock) WARN_ON(sock_owned_by_user(child)); ... sock_orphan(child); // write_lock_bh(&sk->sk_callback_lock) lockdep is not happy with this, as reported by Tetsuo Handa It seems only way to deal with this is to use read_lock_bh(callbacklock) everywhere. Thanks to Jarek for pointing a bug in my first attempt and suggesting this solution. Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Tested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Jarek Poplawski <jarkao2@gmail.com> Tested-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-09-22 19:43:39 +07:00
read_lock_bh(&sk->sk_callback_lock);
uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : GLOBAL_ROOT_UID;
net: fix a lockdep splat We have for each socket : One spinlock (sk_slock.slock) One rwlock (sk_callback_lock) Possible scenarios are : (A) (this is used in net/sunrpc/xprtsock.c) read_lock(&sk->sk_callback_lock) (without blocking BH) <BH> spin_lock(&sk->sk_slock.slock); ... read_lock(&sk->sk_callback_lock); ... (B) write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) (C) spin_lock_bh(&sk->sk_slock) ... write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) spin_unlock_bh(&sk->sk_slock) This (C) case conflicts with (A) : CPU1 [A] CPU2 [C] read_lock(callback_lock) <BH> spin_lock_bh(slock) <wait to spin_lock(slock)> <wait to write_lock_bh(callback_lock)> We have one problematic (C) use case in inet_csk_listen_stop() : local_bh_disable(); bh_lock_sock(child); // spin_lock_bh(&sk->sk_slock) WARN_ON(sock_owned_by_user(child)); ... sock_orphan(child); // write_lock_bh(&sk->sk_callback_lock) lockdep is not happy with this, as reported by Tetsuo Handa It seems only way to deal with this is to use read_lock_bh(callbacklock) everywhere. Thanks to Jarek for pointing a bug in my first attempt and suggesting this solution. Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Tested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Jarek Poplawski <jarkao2@gmail.com> Tested-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-09-22 19:43:39 +07:00
read_unlock_bh(&sk->sk_callback_lock);
return uid;
}
EXPORT_SYMBOL(sock_i_uid);
unsigned long sock_i_ino(struct sock *sk)
{
unsigned long ino;
net: fix a lockdep splat We have for each socket : One spinlock (sk_slock.slock) One rwlock (sk_callback_lock) Possible scenarios are : (A) (this is used in net/sunrpc/xprtsock.c) read_lock(&sk->sk_callback_lock) (without blocking BH) <BH> spin_lock(&sk->sk_slock.slock); ... read_lock(&sk->sk_callback_lock); ... (B) write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) (C) spin_lock_bh(&sk->sk_slock) ... write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) spin_unlock_bh(&sk->sk_slock) This (C) case conflicts with (A) : CPU1 [A] CPU2 [C] read_lock(callback_lock) <BH> spin_lock_bh(slock) <wait to spin_lock(slock)> <wait to write_lock_bh(callback_lock)> We have one problematic (C) use case in inet_csk_listen_stop() : local_bh_disable(); bh_lock_sock(child); // spin_lock_bh(&sk->sk_slock) WARN_ON(sock_owned_by_user(child)); ... sock_orphan(child); // write_lock_bh(&sk->sk_callback_lock) lockdep is not happy with this, as reported by Tetsuo Handa It seems only way to deal with this is to use read_lock_bh(callbacklock) everywhere. Thanks to Jarek for pointing a bug in my first attempt and suggesting this solution. Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Tested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Jarek Poplawski <jarkao2@gmail.com> Tested-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-09-22 19:43:39 +07:00
read_lock_bh(&sk->sk_callback_lock);
ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
net: fix a lockdep splat We have for each socket : One spinlock (sk_slock.slock) One rwlock (sk_callback_lock) Possible scenarios are : (A) (this is used in net/sunrpc/xprtsock.c) read_lock(&sk->sk_callback_lock) (without blocking BH) <BH> spin_lock(&sk->sk_slock.slock); ... read_lock(&sk->sk_callback_lock); ... (B) write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) (C) spin_lock_bh(&sk->sk_slock) ... write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) spin_unlock_bh(&sk->sk_slock) This (C) case conflicts with (A) : CPU1 [A] CPU2 [C] read_lock(callback_lock) <BH> spin_lock_bh(slock) <wait to spin_lock(slock)> <wait to write_lock_bh(callback_lock)> We have one problematic (C) use case in inet_csk_listen_stop() : local_bh_disable(); bh_lock_sock(child); // spin_lock_bh(&sk->sk_slock) WARN_ON(sock_owned_by_user(child)); ... sock_orphan(child); // write_lock_bh(&sk->sk_callback_lock) lockdep is not happy with this, as reported by Tetsuo Handa It seems only way to deal with this is to use read_lock_bh(callbacklock) everywhere. Thanks to Jarek for pointing a bug in my first attempt and suggesting this solution. Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Tested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Jarek Poplawski <jarkao2@gmail.com> Tested-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-09-22 19:43:39 +07:00
read_unlock_bh(&sk->sk_callback_lock);
return ino;
}
EXPORT_SYMBOL(sock_i_ino);
/*
* Allocate a skb from the socket's send buffer.
*/
struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
gfp_t priority)
{
if (force || atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
struct sk_buff *skb = alloc_skb(size, priority);
if (skb) {
skb_set_owner_w(skb, sk);
return skb;
}
}
return NULL;
}
EXPORT_SYMBOL(sock_wmalloc);
/*
* Allocate a memory block from the socket's option memory buffer.
*/
void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
{
if ((unsigned int)size <= sysctl_optmem_max &&
atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
void *mem;
/* First do the add, to avoid the race if kmalloc
* might sleep.
*/
atomic_add(size, &sk->sk_omem_alloc);
mem = kmalloc(size, priority);
if (mem)
return mem;
atomic_sub(size, &sk->sk_omem_alloc);
}
return NULL;
}
EXPORT_SYMBOL(sock_kmalloc);
/* Free an option memory block. Note, we actually want the inline
* here as this allows gcc to detect the nullify and fold away the
* condition entirely.
*/
static inline void __sock_kfree_s(struct sock *sk, void *mem, int size,
const bool nullify)
{
if (WARN_ON_ONCE(!mem))
return;
if (nullify)
kzfree(mem);
else
kfree(mem);
atomic_sub(size, &sk->sk_omem_alloc);
}
void sock_kfree_s(struct sock *sk, void *mem, int size)
{
__sock_kfree_s(sk, mem, size, false);
}
EXPORT_SYMBOL(sock_kfree_s);
void sock_kzfree_s(struct sock *sk, void *mem, int size)
{
__sock_kfree_s(sk, mem, size, true);
}
EXPORT_SYMBOL(sock_kzfree_s);
/* It is almost wait_for_tcp_memory minus release_sock/lock_sock.
I think, these locks should be removed for datagram sockets.
*/
static long sock_wait_for_wmem(struct sock *sk, long timeo)
{
DEFINE_WAIT(wait);
clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
for (;;) {
if (!timeo)
break;
if (signal_pending(current))
break;
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf)
break;
if (sk->sk_shutdown & SEND_SHUTDOWN)
break;
if (sk->sk_err)
break;
timeo = schedule_timeout(timeo);
}
finish_wait(sk_sleep(sk), &wait);
return timeo;
}
/*
* Generic send/receive buffer handlers
*/
struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
unsigned long data_len, int noblock,
int *errcode, int max_page_order)
{
struct sk_buff *skb;
long timeo;
int err;
timeo = sock_sndtimeo(sk, noblock);
for (;;) {
err = sock_error(sk);
if (err != 0)
goto failure;
err = -EPIPE;
if (sk->sk_shutdown & SEND_SHUTDOWN)
goto failure;
if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf)
break;
set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
err = -EAGAIN;
if (!timeo)
goto failure;
if (signal_pending(current))
goto interrupted;
timeo = sock_wait_for_wmem(sk, timeo);
}
skb = alloc_skb_with_frags(header_len, data_len, max_page_order,
errcode, sk->sk_allocation);
if (skb)
skb_set_owner_w(skb, sk);
return skb;
interrupted:
err = sock_intr_errno(timeo);
failure:
*errcode = err;
return NULL;
}
EXPORT_SYMBOL(sock_alloc_send_pskb);
struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
int noblock, int *errcode)
{
return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0);
}
EXPORT_SYMBOL(sock_alloc_send_skb);
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-24 06:04:42 +07:00
/* On 32bit arches, an skb frag is limited to 2^15 */
#define SKB_FRAG_PAGE_ORDER get_order(32768)
/**
* skb_page_frag_refill - check that a page_frag contains enough room
* @sz: minimum size of the fragment we want to get
* @pfrag: pointer to page_frag
* @gfp: priority for memory allocation
*
* Note: While this allocator tries to use high order pages, there is
* no guarantee that allocations succeed. Therefore, @sz MUST be
* less or equal than PAGE_SIZE.
*/
bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp)
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-24 06:04:42 +07:00
{
if (pfrag->page) {
if (atomic_read(&pfrag->page->_count) == 1) {
pfrag->offset = 0;
return true;
}
if (pfrag->offset + sz <= pfrag->size)
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-24 06:04:42 +07:00
return true;
put_page(pfrag->page);
}
pfrag->offset = 0;
if (SKB_FRAG_PAGE_ORDER) {
pfrag->page = alloc_pages((gfp & ~__GFP_WAIT) | __GFP_COMP |
__GFP_NOWARN | __GFP_NORETRY,
SKB_FRAG_PAGE_ORDER);
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-24 06:04:42 +07:00
if (likely(pfrag->page)) {
pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER;
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-24 06:04:42 +07:00
return true;
}
}
pfrag->page = alloc_page(gfp);
if (likely(pfrag->page)) {
pfrag->size = PAGE_SIZE;
return true;
}
return false;
}
EXPORT_SYMBOL(skb_page_frag_refill);
bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
{
if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation)))
return true;
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-24 06:04:42 +07:00
sk_enter_memory_pressure(sk);
sk_stream_moderate_sndbuf(sk);
return false;
}
EXPORT_SYMBOL(sk_page_frag_refill);
static void __lock_sock(struct sock *sk)
__releases(&sk->sk_lock.slock)
__acquires(&sk->sk_lock.slock)
{
DEFINE_WAIT(wait);
for (;;) {
prepare_to_wait_exclusive(&sk->sk_lock.wq, &wait,
TASK_UNINTERRUPTIBLE);
spin_unlock_bh(&sk->sk_lock.slock);
schedule();
spin_lock_bh(&sk->sk_lock.slock);
if (!sock_owned_by_user(sk))
break;
}
finish_wait(&sk->sk_lock.wq, &wait);
}
static void __release_sock(struct sock *sk)
__releases(&sk->sk_lock.slock)
__acquires(&sk->sk_lock.slock)
{
struct sk_buff *skb = sk->sk_backlog.head;
do {
sk->sk_backlog.head = sk->sk_backlog.tail = NULL;
bh_unlock_sock(sk);
do {
struct sk_buff *next = skb->next;
prefetch(next);
WARN_ON_ONCE(skb_dst_is_noref(skb));
skb->next = NULL;
sk_backlog_rcv(sk, skb);
/*
* We are in process context here with softirqs
* disabled, use cond_resched_softirq() to preempt.
* This is safe to do because we've taken the backlog
* queue private:
*/
cond_resched_softirq();
skb = next;
} while (skb != NULL);
bh_lock_sock(sk);
} while ((skb = sk->sk_backlog.head) != NULL);
net: add limit for socket backlog We got system OOM while running some UDP netperf testing on the loopback device. The case is multiple senders sent stream UDP packets to a single receiver via loopback on local host. Of course, the receiver is not able to handle all the packets in time. But we surprisingly found that these packets were not discarded due to the receiver's sk->sk_rcvbuf limit. Instead, they are kept queuing to sk->sk_backlog and finally ate up all the memory. We believe this is a secure hole that a none privileged user can crash the system. The root cause for this problem is, when the receiver is doing __release_sock() (i.e. after userspace recv, kernel udp_recvmsg -> skb_free_datagram_locked -> release_sock), it moves skbs from backlog to sk_receive_queue with the softirq enabled. In the above case, multiple busy senders will almost make it an endless loop. The skbs in the backlog end up eat all the system memory. The issue is not only for UDP. Any protocols using socket backlog is potentially affected. The patch adds limit for socket backlog so that the backlog size cannot be expanded endlessly. Reported-by: Alex Shi <alex.shi@intel.com> Cc: David Miller <davem@davemloft.net> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru Cc: "Pekka Savola (ipv6)" <pekkas@netcore.fi> Cc: Patrick McHardy <kaber@trash.net> Cc: Vlad Yasevich <vladislav.yasevich@hp.com> Cc: Sridhar Samudrala <sri@us.ibm.com> Cc: Jon Maloy <jon.maloy@ericsson.com> Cc: Allan Stephens <allan.stephens@windriver.com> Cc: Andrew Hendry <andrew.hendry@gmail.com> Signed-off-by: Zhu Yi <yi.zhu@intel.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-03-05 01:01:40 +07:00
/*
* Doing the zeroing here guarantee we can not loop forever
* while a wild producer attempts to flood us.
*/
sk->sk_backlog.len = 0;
}
/**
* sk_wait_data - wait for data to arrive at sk_receive_queue
[PATCH] DocBook: changes and extensions to the kernel documentation I have recompiled Linux kernel 2.6.11.5 documentation for me and our university students again. The documentation could be extended for more sources which are equipped by structured comments for recent 2.6 kernels. I have tried to proceed with that task. I have done that more times from 2.6.0 time and it gets boring to do same changes again and again. Linux kernel compiles after changes for i386 and ARM targets. I have added references to some more files into kernel-api book, I have added some section names as well. So please, check that changes do not break something and that categories are not too much skewed. I have changed kernel-doc to accept "fastcall" and "asmlinkage" words reserved by kernel convention. Most of the other changes are modifications in the comments to make kernel-doc happy, accept some parameters description and do not bail out on errors. Changed <pid> to @pid in the description, moved some #ifdef before comments to correct function to comments bindings, etc. You can see result of the modified documentation build at http://cmp.felk.cvut.cz/~pisa/linux/lkdb-2.6.11.tar.gz Some more sources are ready to be included into kernel-doc generated documentation. Sources has been added into kernel-api for now. Some more section names added and probably some more chaos introduced as result of quick cleanup work. Signed-off-by: Pavel Pisa <pisa@cmp.felk.cvut.cz> Signed-off-by: Martin Waitz <tali@admingilde.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 22:59:25 +07:00
* @sk: sock to wait on
* @timeo: for how long
* @skb: last skb seen on sk_receive_queue
*
* Now socket state including sk->sk_err is changed only under lock,
* hence we may omit checks after joining wait queue.
* We check receive queue before schedule() only as optimization;
* it is very likely that release_sock() added new data.
*/
int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)
{
int rc;
DEFINE_WAIT(wait);
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb);
clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
finish_wait(sk_sleep(sk), &wait);
return rc;
}
EXPORT_SYMBOL(sk_wait_data);
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 15:11:19 +07:00
/**
* __sk_mem_schedule - increase sk_forward_alloc and memory_allocated
* @sk: socket
* @size: memory size to allocate
* @kind: allocation type
*
* If kind is SK_MEM_SEND, it means wmem allocation. Otherwise it means
* rmem allocation. This function assumes that protocols which have
* memory_pressure use sk_wmem_queued as write buffer accounting.
*/
int __sk_mem_schedule(struct sock *sk, int size, int kind)
{
struct proto *prot = sk->sk_prot;
int amt = sk_mem_pages(size);
long allocated;
int parent_status = UNDER_LIMIT;
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 15:11:19 +07:00
sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
allocated = sk_memory_allocated_add(sk, amt, &parent_status);
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 15:11:19 +07:00
/* Under limit. */
if (parent_status == UNDER_LIMIT &&
allocated <= sk_prot_mem_limits(sk, 0)) {
sk_leave_memory_pressure(sk);
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 15:11:19 +07:00
return 1;
}
/* Under pressure. (we or our parents) */
if ((parent_status > SOFT_LIMIT) ||
allocated > sk_prot_mem_limits(sk, 1))
sk_enter_memory_pressure(sk);
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 15:11:19 +07:00
/* Over hard limit (we or our parents) */
if ((parent_status == OVER_LIMIT) ||
(allocated > sk_prot_mem_limits(sk, 2)))
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 15:11:19 +07:00
goto suppress_allocation;
/* guarantee minimum buffer size under pressure */
if (kind == SK_MEM_RECV) {
if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0])
return 1;
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 15:11:19 +07:00
} else { /* SK_MEM_SEND */
if (sk->sk_type == SOCK_STREAM) {
if (sk->sk_wmem_queued < prot->sysctl_wmem[0])
return 1;
} else if (atomic_read(&sk->sk_wmem_alloc) <
prot->sysctl_wmem[0])
return 1;
}
if (sk_has_memory_pressure(sk)) {
int alloc;
if (!sk_under_memory_pressure(sk))
return 1;
alloc = sk_sockets_allocated_read_positive(sk);
if (sk_prot_mem_limits(sk, 2) > alloc *
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 15:11:19 +07:00
sk_mem_pages(sk->sk_wmem_queued +
atomic_read(&sk->sk_rmem_alloc) +
sk->sk_forward_alloc))
return 1;
}
suppress_allocation:
if (kind == SK_MEM_SEND && sk->sk_type == SOCK_STREAM) {
sk_stream_moderate_sndbuf(sk);
/* Fail only if socket is _under_ its sndbuf.
* In this case we cannot block, so that we have to fail.
*/
if (sk->sk_wmem_queued + size >= sk->sk_sndbuf)
return 1;
}
trace_sock_exceed_buf_limit(sk, prot, allocated);
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 15:11:19 +07:00
/* Alas. Undo changes. */
sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM;
sk_memory_allocated_sub(sk, amt);
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 15:11:19 +07:00
return 0;
}
EXPORT_SYMBOL(__sk_mem_schedule);
/**
* __sk_mem_reclaim - reclaim memory_allocated
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 15:11:19 +07:00
* @sk: socket
* @amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple)
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 15:11:19 +07:00
*/
void __sk_mem_reclaim(struct sock *sk, int amount)
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 15:11:19 +07:00
{
amount >>= SK_MEM_QUANTUM_SHIFT;
sk_memory_allocated_sub(sk, amount);
sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT;
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 15:11:19 +07:00
if (sk_under_memory_pressure(sk) &&
(sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
sk_leave_memory_pressure(sk);
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 15:11:19 +07:00
}
EXPORT_SYMBOL(__sk_mem_reclaim);
/*
* Set of default routines for initialising struct proto_ops when
* the protocol does not support a particular function. In certain
* cases where it makes no sense for a protocol to have a "do nothing"
* function, some default processing is provided.
*/
int sock_no_bind(struct socket *sock, struct sockaddr *saddr, int len)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_bind);
int sock_no_connect(struct socket *sock, struct sockaddr *saddr,
int len, int flags)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_connect);
int sock_no_socketpair(struct socket *sock1, struct socket *sock2)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_socketpair);
int sock_no_accept(struct socket *sock, struct socket *newsock, int flags)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_accept);
int sock_no_getname(struct socket *sock, struct sockaddr *saddr,
int *len, int peer)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_getname);
unsigned int sock_no_poll(struct file *file, struct socket *sock, poll_table *pt)
{
return 0;
}
EXPORT_SYMBOL(sock_no_poll);
int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_ioctl);
int sock_no_listen(struct socket *sock, int backlog)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_listen);
int sock_no_shutdown(struct socket *sock, int how)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_shutdown);
int sock_no_setsockopt(struct socket *sock, int level, int optname,
char __user *optval, unsigned int optlen)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_setsockopt);
int sock_no_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_getsockopt);
int sock_no_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_sendmsg);
int sock_no_recvmsg(struct socket *sock, struct msghdr *m, size_t len,
int flags)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_recvmsg);
int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma)
{
/* Mirror missing mmap method error code */
return -ENODEV;
}
EXPORT_SYMBOL(sock_no_mmap);
ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags)
{
ssize_t res;
struct msghdr msg = {.msg_flags = flags};
struct kvec iov;
char *kaddr = kmap(page);
iov.iov_base = kaddr + offset;
iov.iov_len = size;
res = kernel_sendmsg(sock, &msg, &iov, 1, size);
kunmap(page);
return res;
}
EXPORT_SYMBOL(sock_no_sendpage);
/*
* Default Socket Callbacks
*/
static void sock_def_wakeup(struct sock *sk)
{
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 18:01:49 +07:00
struct socket_wq *wq;
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (wq_has_sleeper(wq))
wake_up_interruptible_all(&wq->wait);
rcu_read_unlock();
}
static void sock_def_error_report(struct sock *sk)
{
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 18:01:49 +07:00
struct socket_wq *wq;
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (wq_has_sleeper(wq))
wake_up_interruptible_poll(&wq->wait, POLLERR);
sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 18:01:49 +07:00
rcu_read_unlock();
}
static void sock_def_readable(struct sock *sk)
{
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 18:01:49 +07:00
struct socket_wq *wq;
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (wq_has_sleeper(wq))
wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLPRI |
POLLRDNORM | POLLRDBAND);
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 18:01:49 +07:00
rcu_read_unlock();
}
static void sock_def_write_space(struct sock *sk)
{
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 18:01:49 +07:00
struct socket_wq *wq;
rcu_read_lock();
/* Do not wake up a writer until he can make "significant"
* progress. --DaveM
*/
if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 18:01:49 +07:00
wq = rcu_dereference(sk->sk_wq);
if (wq_has_sleeper(wq))
wake_up_interruptible_sync_poll(&wq->wait, POLLOUT |
POLLWRNORM | POLLWRBAND);
/* Should agree with poll, otherwise some programs break */
if (sock_writeable(sk))
sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
}
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 18:01:49 +07:00
rcu_read_unlock();
}
static void sock_def_destruct(struct sock *sk)
{
}
void sk_send_sigurg(struct sock *sk)
{
if (sk->sk_socket && sk->sk_socket->file)
if (send_sigurg(&sk->sk_socket->file->f_owner))
sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI);
}
EXPORT_SYMBOL(sk_send_sigurg);
void sk_reset_timer(struct sock *sk, struct timer_list* timer,
unsigned long expires)
{
if (!mod_timer(timer, expires))
sock_hold(sk);
}
EXPORT_SYMBOL(sk_reset_timer);
void sk_stop_timer(struct sock *sk, struct timer_list* timer)
{
if (del_timer(timer))
__sock_put(sk);
}
EXPORT_SYMBOL(sk_stop_timer);
void sock_init_data(struct socket *sock, struct sock *sk)
{
skb_queue_head_init(&sk->sk_receive_queue);
skb_queue_head_init(&sk->sk_write_queue);
skb_queue_head_init(&sk->sk_error_queue);
sk->sk_send_head = NULL;
init_timer(&sk->sk_timer);
sk->sk_allocation = GFP_KERNEL;
sk->sk_rcvbuf = sysctl_rmem_default;
sk->sk_sndbuf = sysctl_wmem_default;
sk->sk_state = TCP_CLOSE;
sk_set_socket(sk, sock);
sock_set_flag(sk, SOCK_ZAPPED);
if (sock) {
sk->sk_type = sock->type;
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 18:01:49 +07:00
sk->sk_wq = sock->wq;
sock->sk = sk;
} else
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 18:01:49 +07:00
sk->sk_wq = NULL;
spin_lock_init(&sk->sk_dst_lock);
rwlock_init(&sk->sk_callback_lock);
lockdep_set_class_and_name(&sk->sk_callback_lock,
af_callback_keys + sk->sk_family,
af_family_clock_key_strings[sk->sk_family]);
sk->sk_state_change = sock_def_wakeup;
sk->sk_data_ready = sock_def_readable;
sk->sk_write_space = sock_def_write_space;
sk->sk_error_report = sock_def_error_report;
sk->sk_destruct = sock_def_destruct;
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-24 06:04:42 +07:00
sk->sk_frag.page = NULL;
sk->sk_frag.offset = 0;
sk->sk_peek_off = -1;
sk->sk_peer_pid = NULL;
sk->sk_peer_cred = NULL;
sk->sk_write_pending = 0;
sk->sk_rcvlowat = 1;
sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT;
sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
sk->sk_stamp = ktime_set(-1L, 0);
#ifdef CONFIG_NET_RX_BUSY_POLL
sk->sk_napi_id = 0;
sk->sk_ll_usec = sysctl_net_busy_read;
#endif
sk->sk_max_pacing_rate = ~0U;
sk->sk_pacing_rate = ~0U;
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
*/
smp_wmb();
atomic_set(&sk->sk_refcnt, 1);
atomic_set(&sk->sk_drops, 0);
}
EXPORT_SYMBOL(sock_init_data);
void lock_sock_nested(struct sock *sk, int subclass)
{
might_sleep();
spin_lock_bh(&sk->sk_lock.slock);
if (sk->sk_lock.owned)
__lock_sock(sk);
sk->sk_lock.owned = 1;
spin_unlock(&sk->sk_lock.slock);
/*
* The sk_lock has mutex_lock() semantics here:
*/
mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
local_bh_enable();
}
EXPORT_SYMBOL(lock_sock_nested);
void release_sock(struct sock *sk)
{
/*
* The sk_lock has mutex_unlock() semantics:
*/
mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
spin_lock_bh(&sk->sk_lock.slock);
if (sk->sk_backlog.tail)
__release_sock(sk);
tcp: TCP Small Queues This introduce TSQ (TCP Small Queues) TSQ goal is to reduce number of TCP packets in xmit queues (qdisc & device queues), to reduce RTT and cwnd bias, part of the bufferbloat problem. sk->sk_wmem_alloc not allowed to grow above a given limit, allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a given time. TSO packets are sized/capped to half the limit, so that we have two TSO packets in flight, allowing better bandwidth use. As a side effect, setting the limit to 40000 automatically reduces the standard gso max limit (65536) to 40000/2 : It can help to reduce latencies of high prio packets, having smaller TSO packets. This means we divert sock_wfree() to a tcp_wfree() handler, to queue/send following frames when skb_orphan() [2] is called for the already queued skbs. Results on my dev machines (tg3/ixgbe nics) are really impressive, using standard pfifo_fast, and with or without TSO/GSO. Without reduction of nominal bandwidth, we have reduction of buffering per bulk sender : < 1ms on Gbit (instead of 50ms with TSO) < 8ms on 100Mbit (instead of 132 ms) I no longer have 4 MBytes backlogged in qdisc by a single netperf session, and both side socket autotuning no longer use 4 Mbytes. As skb destructor cannot restart xmit itself ( as qdisc lock might be taken at this point ), we delegate the work to a tasklet. We use one tasklest per cpu for performance reasons. If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag. This flag is tested in a new protocol method called from release_sock(), to eventually send new segments. [1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable [2] skb_orphan() is usually called at TX completion time, but some drivers call it in their start_xmit() handler. These drivers should at least use BQL, or else a single TCP session can still fill the whole NIC TX ring, since TSQ will have no effect. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Dave Taht <dave.taht@bufferbloat.net> Cc: Tom Herbert <therbert@google.com> Cc: Matt Mathis <mattmathis@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Nandita Dukkipati <nanditad@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-07-11 12:50:31 +07:00
tcp: tcp_release_cb() should release socket ownership Lars Persson reported following deadlock : -000 |M:0x0:0x802B6AF8(asm) <-- arch_spin_lock -001 |tcp_v4_rcv(skb = 0x8BD527A0) <-- sk = 0x8BE6B2A0 -002 |ip_local_deliver_finish(skb = 0x8BD527A0) -003 |__netif_receive_skb_core(skb = 0x8BD527A0, ?) -004 |netif_receive_skb(skb = 0x8BD527A0) -005 |elk_poll(napi = 0x8C770500, budget = 64) -006 |net_rx_action(?) -007 |__do_softirq() -008 |do_softirq() -009 |local_bh_enable() -010 |tcp_rcv_established(sk = 0x8BE6B2A0, skb = 0x87D3A9E0, th = 0x814EBE14, ?) -011 |tcp_v4_do_rcv(sk = 0x8BE6B2A0, skb = 0x87D3A9E0) -012 |tcp_delack_timer_handler(sk = 0x8BE6B2A0) -013 |tcp_release_cb(sk = 0x8BE6B2A0) -014 |release_sock(sk = 0x8BE6B2A0) -015 |tcp_sendmsg(?, sk = 0x8BE6B2A0, ?, ?) -016 |sock_sendmsg(sock = 0x8518C4C0, msg = 0x87D8DAA8, size = 4096) -017 |kernel_sendmsg(?, ?, ?, ?, size = 4096) -018 |smb_send_kvec() -019 |smb_send_rqst(server = 0x87C4D400, rqst = 0x87D8DBA0) -020 |cifs_call_async() -021 |cifs_async_writev(wdata = 0x87FD6580) -022 |cifs_writepages(mapping = 0x852096E4, wbc = 0x87D8DC88) -023 |__writeback_single_inode(inode = 0x852095D0, wbc = 0x87D8DC88) -024 |writeback_sb_inodes(sb = 0x87D6D800, wb = 0x87E4A9C0, work = 0x87D8DD88) -025 |__writeback_inodes_wb(wb = 0x87E4A9C0, work = 0x87D8DD88) -026 |wb_writeback(wb = 0x87E4A9C0, work = 0x87D8DD88) -027 |wb_do_writeback(wb = 0x87E4A9C0, force_wait = 0) -028 |bdi_writeback_workfn(work = 0x87E4A9CC) -029 |process_one_work(worker = 0x8B045880, work = 0x87E4A9CC) -030 |worker_thread(__worker = 0x8B045880) -031 |kthread(_create = 0x87CADD90) -032 |ret_from_kernel_thread(asm) Bug occurs because __tcp_checksum_complete_user() enables BH, assuming it is running from softirq context. Lars trace involved a NIC without RX checksum support but other points are problematic as well, like the prequeue stuff. Problem is triggered by a timer, that found socket being owned by user. tcp_release_cb() should call tcp_write_timer_handler() or tcp_delack_timer_handler() in the appropriate context : BH disabled and socket lock held, but 'owned' field cleared, as if they were running from timer handlers. Fixes: 6f458dfb4092 ("tcp: improve latencies of timer triggered events") Reported-by: Lars Persson <lars.persson@axis.com> Tested-by: Lars Persson <lars.persson@axis.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-10 23:50:11 +07:00
/* Warning : release_cb() might need to release sk ownership,
* ie call sock_release_ownership(sk) before us.
*/
tcp: TCP Small Queues This introduce TSQ (TCP Small Queues) TSQ goal is to reduce number of TCP packets in xmit queues (qdisc & device queues), to reduce RTT and cwnd bias, part of the bufferbloat problem. sk->sk_wmem_alloc not allowed to grow above a given limit, allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a given time. TSO packets are sized/capped to half the limit, so that we have two TSO packets in flight, allowing better bandwidth use. As a side effect, setting the limit to 40000 automatically reduces the standard gso max limit (65536) to 40000/2 : It can help to reduce latencies of high prio packets, having smaller TSO packets. This means we divert sock_wfree() to a tcp_wfree() handler, to queue/send following frames when skb_orphan() [2] is called for the already queued skbs. Results on my dev machines (tg3/ixgbe nics) are really impressive, using standard pfifo_fast, and with or without TSO/GSO. Without reduction of nominal bandwidth, we have reduction of buffering per bulk sender : < 1ms on Gbit (instead of 50ms with TSO) < 8ms on 100Mbit (instead of 132 ms) I no longer have 4 MBytes backlogged in qdisc by a single netperf session, and both side socket autotuning no longer use 4 Mbytes. As skb destructor cannot restart xmit itself ( as qdisc lock might be taken at this point ), we delegate the work to a tasklet. We use one tasklest per cpu for performance reasons. If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag. This flag is tested in a new protocol method called from release_sock(), to eventually send new segments. [1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable [2] skb_orphan() is usually called at TX completion time, but some drivers call it in their start_xmit() handler. These drivers should at least use BQL, or else a single TCP session can still fill the whole NIC TX ring, since TSQ will have no effect. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Dave Taht <dave.taht@bufferbloat.net> Cc: Tom Herbert <therbert@google.com> Cc: Matt Mathis <mattmathis@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Nandita Dukkipati <nanditad@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-07-11 12:50:31 +07:00
if (sk->sk_prot->release_cb)
sk->sk_prot->release_cb(sk);
tcp: tcp_release_cb() should release socket ownership Lars Persson reported following deadlock : -000 |M:0x0:0x802B6AF8(asm) <-- arch_spin_lock -001 |tcp_v4_rcv(skb = 0x8BD527A0) <-- sk = 0x8BE6B2A0 -002 |ip_local_deliver_finish(skb = 0x8BD527A0) -003 |__netif_receive_skb_core(skb = 0x8BD527A0, ?) -004 |netif_receive_skb(skb = 0x8BD527A0) -005 |elk_poll(napi = 0x8C770500, budget = 64) -006 |net_rx_action(?) -007 |__do_softirq() -008 |do_softirq() -009 |local_bh_enable() -010 |tcp_rcv_established(sk = 0x8BE6B2A0, skb = 0x87D3A9E0, th = 0x814EBE14, ?) -011 |tcp_v4_do_rcv(sk = 0x8BE6B2A0, skb = 0x87D3A9E0) -012 |tcp_delack_timer_handler(sk = 0x8BE6B2A0) -013 |tcp_release_cb(sk = 0x8BE6B2A0) -014 |release_sock(sk = 0x8BE6B2A0) -015 |tcp_sendmsg(?, sk = 0x8BE6B2A0, ?, ?) -016 |sock_sendmsg(sock = 0x8518C4C0, msg = 0x87D8DAA8, size = 4096) -017 |kernel_sendmsg(?, ?, ?, ?, size = 4096) -018 |smb_send_kvec() -019 |smb_send_rqst(server = 0x87C4D400, rqst = 0x87D8DBA0) -020 |cifs_call_async() -021 |cifs_async_writev(wdata = 0x87FD6580) -022 |cifs_writepages(mapping = 0x852096E4, wbc = 0x87D8DC88) -023 |__writeback_single_inode(inode = 0x852095D0, wbc = 0x87D8DC88) -024 |writeback_sb_inodes(sb = 0x87D6D800, wb = 0x87E4A9C0, work = 0x87D8DD88) -025 |__writeback_inodes_wb(wb = 0x87E4A9C0, work = 0x87D8DD88) -026 |wb_writeback(wb = 0x87E4A9C0, work = 0x87D8DD88) -027 |wb_do_writeback(wb = 0x87E4A9C0, force_wait = 0) -028 |bdi_writeback_workfn(work = 0x87E4A9CC) -029 |process_one_work(worker = 0x8B045880, work = 0x87E4A9CC) -030 |worker_thread(__worker = 0x8B045880) -031 |kthread(_create = 0x87CADD90) -032 |ret_from_kernel_thread(asm) Bug occurs because __tcp_checksum_complete_user() enables BH, assuming it is running from softirq context. Lars trace involved a NIC without RX checksum support but other points are problematic as well, like the prequeue stuff. Problem is triggered by a timer, that found socket being owned by user. tcp_release_cb() should call tcp_write_timer_handler() or tcp_delack_timer_handler() in the appropriate context : BH disabled and socket lock held, but 'owned' field cleared, as if they were running from timer handlers. Fixes: 6f458dfb4092 ("tcp: improve latencies of timer triggered events") Reported-by: Lars Persson <lars.persson@axis.com> Tested-by: Lars Persson <lars.persson@axis.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-10 23:50:11 +07:00
sock_release_ownership(sk);
if (waitqueue_active(&sk->sk_lock.wq))
wake_up(&sk->sk_lock.wq);
spin_unlock_bh(&sk->sk_lock.slock);
}
EXPORT_SYMBOL(release_sock);
/**
* lock_sock_fast - fast version of lock_sock
* @sk: socket
*
* This version should be used for very small section, where process wont block
* return false if fast path is taken
* sk_lock.slock locked, owned = 0, BH disabled
* return true if slow path is taken
* sk_lock.slock unlocked, owned = 1, BH enabled
*/
bool lock_sock_fast(struct sock *sk)
{
might_sleep();
spin_lock_bh(&sk->sk_lock.slock);
if (!sk->sk_lock.owned)
/*
* Note : We must disable BH
*/
return false;
__lock_sock(sk);
sk->sk_lock.owned = 1;
spin_unlock(&sk->sk_lock.slock);
/*
* The sk_lock has mutex_lock() semantics here:
*/
mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_);
local_bh_enable();
return true;
}
EXPORT_SYMBOL(lock_sock_fast);
int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
{
struct timeval tv;
if (!sock_flag(sk, SOCK_TIMESTAMP))
sock_enable_timestamp(sk, SOCK_TIMESTAMP);
tv = ktime_to_timeval(sk->sk_stamp);
if (tv.tv_sec == -1)
return -ENOENT;
if (tv.tv_sec == 0) {
sk->sk_stamp = ktime_get_real();
tv = ktime_to_timeval(sk->sk_stamp);
}
return copy_to_user(userstamp, &tv, sizeof(tv)) ? -EFAULT : 0;
}
EXPORT_SYMBOL(sock_get_timestamp);
int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
{
struct timespec ts;
if (!sock_flag(sk, SOCK_TIMESTAMP))
sock_enable_timestamp(sk, SOCK_TIMESTAMP);
ts = ktime_to_timespec(sk->sk_stamp);
if (ts.tv_sec == -1)
return -ENOENT;
if (ts.tv_sec == 0) {
sk->sk_stamp = ktime_get_real();
ts = ktime_to_timespec(sk->sk_stamp);
}
return copy_to_user(userstamp, &ts, sizeof(ts)) ? -EFAULT : 0;
}
EXPORT_SYMBOL(sock_get_timestampns);
void sock_enable_timestamp(struct sock *sk, int flag)
{
if (!sock_flag(sk, flag)) {
unsigned long previous_flags = sk->sk_flags;
sock_set_flag(sk, flag);
/*
* we just set one of the two flags which require net
* time stamping, but time stamping might have been on
* already because of the other one
*/
if (!(previous_flags & SK_FLAGS_TIMESTAMP))
net_enable_timestamp();
}
}
int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len,
int level, int type)
{
struct sock_exterr_skb *serr;
struct sk_buff *skb;
int copied, err;
err = -EAGAIN;
skb = sock_dequeue_err_skb(sk);
if (skb == NULL)
goto out;
copied = skb->len;
if (copied > len) {
msg->msg_flags |= MSG_TRUNC;
copied = len;
}
err = skb_copy_datagram_msg(skb, 0, msg, copied);
if (err)
goto out_free_skb;
sock_recv_timestamp(msg, sk, skb);
serr = SKB_EXT_ERR(skb);
put_cmsg(msg, level, type, sizeof(serr->ee), &serr->ee);
msg->msg_flags |= MSG_ERRQUEUE;
err = copied;
out_free_skb:
kfree_skb(skb);
out:
return err;
}
EXPORT_SYMBOL(sock_recv_errqueue);
/*
* Get a socket option on an socket.
*
* FIX: POSIX 1003.1g is very ambiguous here. It states that
* asynchronous errors should be reported by getsockopt. We assume
* this means if you specify SO_ERROR (otherwise whats the point of it).
*/
int sock_common_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen)
{
struct sock *sk = sock->sk;
return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(sock_common_getsockopt);
#ifdef CONFIG_COMPAT
int compat_sock_common_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen)
{
struct sock *sk = sock->sk;
if (sk->sk_prot->compat_getsockopt != NULL)
return sk->sk_prot->compat_getsockopt(sk, level, optname,
optval, optlen);
return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(compat_sock_common_getsockopt);
#endif
int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int flags)
{
struct sock *sk = sock->sk;
int addr_len = 0;
int err;
err = sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
flags & ~MSG_DONTWAIT, &addr_len);
if (err >= 0)
msg->msg_namelen = addr_len;
return err;
}
EXPORT_SYMBOL(sock_common_recvmsg);
/*
* Set socket options on an inet socket.
*/
int sock_common_setsockopt(struct socket *sock, int level, int optname,
char __user *optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(sock_common_setsockopt);
#ifdef CONFIG_COMPAT
int compat_sock_common_setsockopt(struct socket *sock, int level, int optname,
char __user *optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
if (sk->sk_prot->compat_setsockopt != NULL)
return sk->sk_prot->compat_setsockopt(sk, level, optname,
optval, optlen);
return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(compat_sock_common_setsockopt);
#endif
void sk_common_release(struct sock *sk)
{
if (sk->sk_prot->destroy)
sk->sk_prot->destroy(sk);
/*
* Observation: when sock_common_release is called, processes have
* no access to socket. But net still has.
* Step one, detach it from networking:
*
* A. Remove from hash tables.
*/
sk->sk_prot->unhash(sk);
/*
* In this point socket cannot receive new packets, but it is possible
* that some packets are in flight because some CPU runs receiver and
* did hash table lookup before we unhashed socket. They will achieve
* receive queue and will be purged by socket destructor.
*
* Also we still have packets pending on receive queue and probably,
* our own packets waiting in device queues. sock_destroy will drain
* receive queue, but transmitted packets will delay socket destruction
* until the last reference will be released.
*/
sock_orphan(sk);
xfrm_sk_free_policy(sk);
sk_refcnt_debug_release(sk);
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-24 06:04:42 +07:00
if (sk->sk_frag.page) {
put_page(sk->sk_frag.page);
sk->sk_frag.page = NULL;
}
sock_put(sk);
}
EXPORT_SYMBOL(sk_common_release);
#ifdef CONFIG_PROC_FS
#define PROTO_INUSE_NR 64 /* should be enough for the first time */
struct prot_inuse {
int val[PROTO_INUSE_NR];
};
static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR);
#ifdef CONFIG_NET_NS
void sock_prot_inuse_add(struct net *net, struct proto *prot, int val)
{
__this_cpu_add(net->core.inuse->val[prot->inuse_idx], val);
}
EXPORT_SYMBOL_GPL(sock_prot_inuse_add);
int sock_prot_inuse_get(struct net *net, struct proto *prot)
{
int cpu, idx = prot->inuse_idx;
int res = 0;
for_each_possible_cpu(cpu)
res += per_cpu_ptr(net->core.inuse, cpu)->val[idx];
return res >= 0 ? res : 0;
}
EXPORT_SYMBOL_GPL(sock_prot_inuse_get);
static int __net_init sock_inuse_init_net(struct net *net)
{
net->core.inuse = alloc_percpu(struct prot_inuse);
return net->core.inuse ? 0 : -ENOMEM;
}
static void __net_exit sock_inuse_exit_net(struct net *net)
{
free_percpu(net->core.inuse);
}
static struct pernet_operations net_inuse_ops = {
.init = sock_inuse_init_net,
.exit = sock_inuse_exit_net,
};
static __init int net_inuse_init(void)
{
if (register_pernet_subsys(&net_inuse_ops))
panic("Cannot initialize net inuse counters");
return 0;
}
core_initcall(net_inuse_init);
#else
static DEFINE_PER_CPU(struct prot_inuse, prot_inuse);
void sock_prot_inuse_add(struct net *net, struct proto *prot, int val)
{
__this_cpu_add(prot_inuse.val[prot->inuse_idx], val);
}
EXPORT_SYMBOL_GPL(sock_prot_inuse_add);
int sock_prot_inuse_get(struct net *net, struct proto *prot)
{
int cpu, idx = prot->inuse_idx;
int res = 0;
for_each_possible_cpu(cpu)
res += per_cpu(prot_inuse, cpu).val[idx];
return res >= 0 ? res : 0;
}
EXPORT_SYMBOL_GPL(sock_prot_inuse_get);
#endif
static void assign_proto_idx(struct proto *prot)
{
prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR);
if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) {
pr_err("PROTO_INUSE_NR exhausted\n");
return;
}
set_bit(prot->inuse_idx, proto_inuse_idx);
}
static void release_proto_idx(struct proto *prot)
{
if (prot->inuse_idx != PROTO_INUSE_NR - 1)
clear_bit(prot->inuse_idx, proto_inuse_idx);
}
#else
static inline void assign_proto_idx(struct proto *prot)
{
}
static inline void release_proto_idx(struct proto *prot)
{
}
#endif
static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
{
if (!rsk_prot)
return;
kfree(rsk_prot->slab_name);
rsk_prot->slab_name = NULL;
kmem_cache_destroy(rsk_prot->slab);
rsk_prot->slab = NULL;
}
static int req_prot_init(const struct proto *prot)
{
struct request_sock_ops *rsk_prot = prot->rsk_prot;
if (!rsk_prot)
return 0;
rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s",
prot->name);
if (!rsk_prot->slab_name)
return -ENOMEM;
rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name,
rsk_prot->obj_size, 0,
0, NULL);
if (!rsk_prot->slab) {
pr_crit("%s: Can't create request sock SLAB cache!\n",
prot->name);
return -ENOMEM;
}
return 0;
}
int proto_register(struct proto *prot, int alloc_slab)
{
if (alloc_slab) {
prot->slab = kmem_cache_create(prot->name, prot->obj_size, 0,
udp: RCU handling for Unicast packets. Goals are : 1) Optimizing handling of incoming Unicast UDP frames, so that no memory writes should happen in the fast path. Note: Multicasts and broadcasts still will need to take a lock, because doing a full lockless lookup in this case is difficult. 2) No expensive operations in the socket bind/unhash phases : - No expensive synchronize_rcu() calls. - No added rcu_head in socket structure, increasing memory needs, but more important, forcing us to use call_rcu() calls, that have the bad property of making sockets structure cold. (rcu grace period between socket freeing and its potential reuse make this socket being cold in CPU cache). David did a previous patch using call_rcu() and noticed a 20% impact on TCP connection rates. Quoting Cristopher Lameter : "Right. That results in cacheline cooldown. You'd want to recycle the object as they are cache hot on a per cpu basis. That is screwed up by the delayed regular rcu processing. We have seen multiple regressions due to cacheline cooldown. The only choice in cacheline hot sensitive areas is to deal with the complexity that comes with SLAB_DESTROY_BY_RCU or give up on RCU." - Because udp sockets are allocated from dedicated kmem_cache, use of SLAB_DESTROY_BY_RCU can help here. Theory of operation : --------------------- As the lookup is lockfree (using rcu_read_lock()/rcu_read_unlock()), special attention must be taken by readers and writers. Use of SLAB_DESTROY_BY_RCU is tricky too, because a socket can be freed, reused, inserted in a different chain or in worst case in the same chain while readers could do lookups in the same time. In order to avoid loops, a reader must check each socket found in a chain really belongs to the chain the reader was traversing. If it finds a mismatch, lookup must start again at the begining. This *restart* loop is the reason we had to use rdlock for the multicast case, because we dont want to send same message several times to the same socket. We use RCU only for fast path. Thus, /proc/net/udp still takes spinlocks. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-29 16:11:14 +07:00
SLAB_HWCACHE_ALIGN | prot->slab_flags,
NULL);
if (prot->slab == NULL) {
pr_crit("%s: Can't create sock SLAB cache!\n",
prot->name);
goto out;
}
if (req_prot_init(prot))
goto out_free_request_sock_slab;
if (prot->twsk_prot != NULL) {
prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name);
if (prot->twsk_prot->twsk_slab_name == NULL)
goto out_free_request_sock_slab;
prot->twsk_prot->twsk_slab =
kmem_cache_create(prot->twsk_prot->twsk_slab_name,
prot->twsk_prot->twsk_obj_size,
0,
prot->slab_flags,
NULL);
if (prot->twsk_prot->twsk_slab == NULL)
goto out_free_timewait_sock_slab_name;
}
}
mutex_lock(&proto_list_mutex);
list_add(&prot->node, &proto_list);
assign_proto_idx(prot);
mutex_unlock(&proto_list_mutex);
return 0;
out_free_timewait_sock_slab_name:
kfree(prot->twsk_prot->twsk_slab_name);
out_free_request_sock_slab:
req_prot_cleanup(prot->rsk_prot);
kmem_cache_destroy(prot->slab);
prot->slab = NULL;
out:
return -ENOBUFS;
}
EXPORT_SYMBOL(proto_register);
void proto_unregister(struct proto *prot)
{
mutex_lock(&proto_list_mutex);
release_proto_idx(prot);
list_del(&prot->node);
mutex_unlock(&proto_list_mutex);
kmem_cache_destroy(prot->slab);
prot->slab = NULL;
req_prot_cleanup(prot->rsk_prot);
if (prot->twsk_prot != NULL && prot->twsk_prot->twsk_slab != NULL) {
kmem_cache_destroy(prot->twsk_prot->twsk_slab);
kfree(prot->twsk_prot->twsk_slab_name);
prot->twsk_prot->twsk_slab = NULL;
}
}
EXPORT_SYMBOL(proto_unregister);
#ifdef CONFIG_PROC_FS
static void *proto_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(proto_list_mutex)
{
mutex_lock(&proto_list_mutex);
return seq_list_start_head(&proto_list, *pos);
}
static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
return seq_list_next(v, &proto_list, pos);
}
static void proto_seq_stop(struct seq_file *seq, void *v)
__releases(proto_list_mutex)
{
mutex_unlock(&proto_list_mutex);
}
static char proto_method_implemented(const void *method)
{
return method == NULL ? 'n' : 'y';
}
static long sock_prot_memory_allocated(struct proto *proto)
{
return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L;
}
static char *sock_prot_memory_pressure(struct proto *proto)
{
return proto->memory_pressure != NULL ?
proto_memory_pressure(proto) ? "yes" : "no" : "NI";
}
static void proto_seq_printf(struct seq_file *seq, struct proto *proto)
{
seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s "
"%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n",
proto->name,
proto->obj_size,
sock_prot_inuse_get(seq_file_net(seq), proto),
sock_prot_memory_allocated(proto),
sock_prot_memory_pressure(proto),
proto->max_header,
proto->slab == NULL ? "no" : "yes",
module_name(proto->owner),
proto_method_implemented(proto->close),
proto_method_implemented(proto->connect),
proto_method_implemented(proto->disconnect),
proto_method_implemented(proto->accept),
proto_method_implemented(proto->ioctl),
proto_method_implemented(proto->init),
proto_method_implemented(proto->destroy),
proto_method_implemented(proto->shutdown),
proto_method_implemented(proto->setsockopt),
proto_method_implemented(proto->getsockopt),
proto_method_implemented(proto->sendmsg),
proto_method_implemented(proto->recvmsg),
proto_method_implemented(proto->sendpage),
proto_method_implemented(proto->bind),
proto_method_implemented(proto->backlog_rcv),
proto_method_implemented(proto->hash),
proto_method_implemented(proto->unhash),
proto_method_implemented(proto->get_port),
proto_method_implemented(proto->enter_memory_pressure));
}
static int proto_seq_show(struct seq_file *seq, void *v)
{
if (v == &proto_list)
seq_printf(seq, "%-9s %-4s %-8s %-6s %-5s %-7s %-4s %-10s %s",
"protocol",
"size",
"sockets",
"memory",
"press",
"maxhdr",
"slab",
"module",
"cl co di ac io in de sh ss gs se re sp bi br ha uh gp em\n");
else
proto_seq_printf(seq, list_entry(v, struct proto, node));
return 0;
}
static const struct seq_operations proto_seq_ops = {
.start = proto_seq_start,
.next = proto_seq_next,
.stop = proto_seq_stop,
.show = proto_seq_show,
};
static int proto_seq_open(struct inode *inode, struct file *file)
{
return seq_open_net(inode, file, &proto_seq_ops,
sizeof(struct seq_net_private));
}
static const struct file_operations proto_seq_fops = {
.owner = THIS_MODULE,
.open = proto_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_net,
};
static __net_init int proto_init_net(struct net *net)
{
if (!proc_create("protocols", S_IRUGO, net->proc_net, &proto_seq_fops))
return -ENOMEM;
return 0;
}
static __net_exit void proto_exit_net(struct net *net)
{
remove_proc_entry("protocols", net->proc_net);
}
static __net_initdata struct pernet_operations proto_net_ops = {
.init = proto_init_net,
.exit = proto_exit_net,
};
static int __init proto_init(void)
{
return register_pernet_subsys(&proto_net_ops);
}
subsys_initcall(proto_init);
#endif /* PROC_FS */