Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1765419AbYBTPXZ (ORCPT ); Wed, 20 Feb 2008 10:23:25 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1764297AbYBTPT1 (ORCPT ); Wed, 20 Feb 2008 10:19:27 -0500 Received: from viefep18-int.chello.at ([213.46.255.22]:42513 "EHLO viefep16-int.chello.at" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1753370AbYBTPSh (ORCPT ); Wed, 20 Feb 2008 10:18:37 -0500 X-SourceIP: 80.56.237.116 Message-Id: <20080220150307.208040000@chello.nl> References: <20080220144610.548202000@chello.nl> User-Agent: quilt/0.45-1 Date: Wed, 20 Feb 2008 15:46:25 +0100 From: Peter Zijlstra To: Linus Torvalds , Andrew Morton , linux-kernel@vger.kernel.org, linux-mm@kvack.org, netdev@vger.kernel.org, trond.myklebust@fys.uio.no Cc: Peter Zijlstra Subject: [PATCH 15/28] netvm: network reserve infrastructure Content-Disposition: inline; filename=netvm-reserve.patch Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7549 Lines: 263 Provide the basic infrastructure to reserve and charge/account network memory. We provide the following reserve tree: 1) total network reserve 2) network TX reserve 3) protocol TX pages 4) network RX reserve 5) SKB data reserve [1] is used to make all the network reserves a single subtree, for easy manipulation. [2] and [4] are merely for eastetic reasons. The TX pages reserve [3] is assumed bounded by it being the upper bound of memory that can be used for sending pages (not quite true, but good enough) The SKB reserve [5] is an aggregate reserve, which is used to charge SKB data against in the fallback path. The consumers for these reserves are sockets marked with: SOCK_MEMALLOC Such sockets are to be used to service the VM (iow. to swap over). They must be handled kernel side, exposing such a socket to user-space is a BUG. Signed-off-by: Peter Zijlstra --- include/net/sock.h | 35 +++++++++++++++- net/Kconfig | 3 + net/core/sock.c | 113 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 150 insertions(+), 1 deletion(-) Index: linux-2.6/include/net/sock.h =================================================================== --- linux-2.6.orig/include/net/sock.h +++ linux-2.6/include/net/sock.h @@ -51,6 +51,7 @@ #include /* struct sk_buff */ #include #include +#include #include @@ -405,6 +406,7 @@ enum sock_flags { SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */ SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */ SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */ + SOCK_MEMALLOC, /* the VM depends on us - make sure we're serviced */ }; static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) @@ -427,9 +429,40 @@ static inline int sock_flag(struct sock return test_bit(flag, &sk->sk_flags); } +static inline int sk_has_memalloc(struct sock *sk) +{ + return sock_flag(sk, SOCK_MEMALLOC); +} + +/* + * Guestimate the per request queue TX upper bound. + * + * Max packet size is 64k, and we need to reserve that much since the data + * might need to bounce it. Double it to be on the safe side. + */ +#define TX_RESERVE_PAGES DIV_ROUND_UP(2*65536, PAGE_SIZE) + +extern atomic_t memalloc_socks; + +extern struct mem_reserve net_rx_reserve; +extern struct mem_reserve net_skb_reserve; + +static inline int sk_memalloc_socks(void) +{ + return atomic_read(&memalloc_socks); +} + +extern int rx_emergency_get(int bytes); +extern int rx_emergency_get_overcommit(int bytes); +extern void rx_emergency_put(int bytes); + +extern int sk_adjust_memalloc(int socks, long tx_reserve_pages); +extern int sk_set_memalloc(struct sock *sk); +extern int sk_clear_memalloc(struct sock *sk); + static inline gfp_t sk_allocation(struct sock *sk, gfp_t gfp_mask) { - return gfp_mask; + return gfp_mask | (sk->sk_allocation & __GFP_MEMALLOC); } static inline void sk_acceptq_removed(struct sock *sk) Index: linux-2.6/net/core/sock.c =================================================================== --- linux-2.6.orig/net/core/sock.c +++ linux-2.6/net/core/sock.c @@ -112,6 +112,7 @@ #include #include #include +#include #include #include @@ -213,6 +214,111 @@ __u32 sysctl_rmem_default __read_mostly /* Maximal space eaten by iovec or ancilliary data plus some space */ int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); +atomic_t memalloc_socks; + +static struct mem_reserve net_reserve; +struct mem_reserve net_rx_reserve; +EXPORT_SYMBOL_GPL(net_rx_reserve); /* modular ipv6 only */ +struct mem_reserve net_skb_reserve; +EXPORT_SYMBOL_GPL(net_skb_reserve); /* modular ipv6 only */ +static struct mem_reserve net_tx_reserve; +static struct mem_reserve net_tx_pages; + + +/* + * is there room for another emergency packet? + */ +static int __rx_emergency_get(int bytes, bool overcommit) +{ + return mem_reserve_kmalloc_charge(&net_skb_reserve, bytes, overcommit); +} + +int rx_emergency_get(int bytes) +{ + return __rx_emergency_get(bytes, false); +} + +int rx_emergency_get_overcommit(int bytes) +{ + return __rx_emergency_get(bytes, true); +} + +void rx_emergency_put(int bytes) +{ + mem_reserve_kmalloc_charge(&net_skb_reserve, -bytes, 0); +} + +/** + * sk_adjust_memalloc - adjust the global memalloc reserve for critical RX + * @socks: number of new %SOCK_MEMALLOC sockets + * @tx_resserve_pages: number of pages to (un)reserve for TX + * + * This function adjusts the memalloc reserve based on system demand. + * The RX reserve is a limit, and only added once, not for each socket. + * + * NOTE: + * @tx_reserve_pages is an upper-bound of memory used for TX hence + * we need not account the pages like we do for RX pages. + */ +int sk_adjust_memalloc(int socks, long tx_reserve_pages) +{ + int nr_socks; + int err; + + err = mem_reserve_pages_add(&net_tx_pages, tx_reserve_pages); + if (err) + return err; + + nr_socks = atomic_read(&memalloc_socks); + if (!nr_socks && socks > 0) + err = mem_reserve_connect(&net_reserve, &mem_reserve_root); + nr_socks = atomic_add_return(socks, &memalloc_socks); + if (!nr_socks && socks) + err = mem_reserve_disconnect(&net_reserve); + + if (err) + mem_reserve_pages_add(&net_tx_pages, -tx_reserve_pages); + + return err; +} + +/** + * sk_set_memalloc - sets %SOCK_MEMALLOC + * @sk: socket to set it on + * + * Set %SOCK_MEMALLOC on a socket and increase the memalloc reserve + * accordingly. + */ +int sk_set_memalloc(struct sock *sk) +{ + int set = sock_flag(sk, SOCK_MEMALLOC); +#ifndef CONFIG_NETVM + BUG(); +#endif + if (!set) { + int err = sk_adjust_memalloc(1, 0); + if (err) + return err; + + sock_set_flag(sk, SOCK_MEMALLOC); + sk->sk_allocation |= __GFP_MEMALLOC; + } + return !set; +} +EXPORT_SYMBOL_GPL(sk_set_memalloc); + +int sk_clear_memalloc(struct sock *sk) +{ + int set = sock_flag(sk, SOCK_MEMALLOC); + if (set) { + sk_adjust_memalloc(-1, 0); + sock_reset_flag(sk, SOCK_MEMALLOC); + sk->sk_allocation &= ~__GFP_MEMALLOC; + } + return set; +} +EXPORT_SYMBOL_GPL(sk_clear_memalloc); + static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) { struct timeval tv; @@ -968,6 +1074,7 @@ void sk_free(struct sock *sk) { struct sk_filter *filter; + sk_clear_memalloc(sk); if (sk->sk_destruct) sk->sk_destruct(sk); @@ -1095,6 +1202,12 @@ void __init sk_init(void) sysctl_wmem_max = 131071; sysctl_rmem_max = 131071; } + + mem_reserve_init(&net_reserve, "total network reserve", NULL); + mem_reserve_init(&net_rx_reserve, "network RX reserve", &net_reserve); + mem_reserve_init(&net_skb_reserve, "SKB data reserve", &net_rx_reserve); + mem_reserve_init(&net_tx_reserve, "network TX reserve", &net_reserve); + mem_reserve_init(&net_tx_pages, "protocol TX pages", &net_tx_reserve); } /* Index: linux-2.6/net/Kconfig =================================================================== --- linux-2.6.orig/net/Kconfig +++ linux-2.6/net/Kconfig @@ -250,6 +250,9 @@ endmenu source "net/rfkill/Kconfig" source "net/9p/Kconfig" +config NETVM + def_bool n + endif # if NET endmenu # Networking -- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/