From: Xiaotian Feng Subject: [PATCH -mmotm 15/30] netvm: network reserve infrastructure Date: Tue, 13 Jul 2010 06:19:40 -0400 Message-ID: <20100713101939.2835.90633.sendpatchset@danny.redhat> References: <20100713101650.2835.15245.sendpatchset@danny.redhat> Cc: riel@redhat.com, cl@linux-foundation.org, a.p.zijlstra@chello.nl, Xiaotian Feng , linux-kernel@vger.kernel.org, lwang@redhat.com, penberg@cs.helsinki.fi, akpm@linux-foundation.org, davem@davemloft.net To: linux-mm@kvack.org, linux-nfs@vger.kernel.org, netdev@vger.kernel.org Return-path: In-Reply-To: <20100713101650.2835.15245.sendpatchset@danny.redhat> Sender: owner-linux-mm@kvack.org List-ID: >From e8a09c013cf8416ece804ddcbc0d016d2f936e6d Mon Sep 17 00:00:00 2001 From: Xiaotian Feng Date: Tue, 13 Jul 2010 11:06:54 +0800 Subject: [PATCH 15/30] netvm: network reserve infrastructure 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 Signed-off-by: Suresh Jayaraman Signed-off-by: Xiaotian Feng --- include/net/sock.h | 43 ++++++++++++++++++++- net/Kconfig | 3 + net/core/sock.c | 107 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 152 insertions(+), 1 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 9ddb37b..1de14b6 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -52,6 +52,7 @@ #include #include #include +#include #include #include @@ -532,6 +533,7 @@ 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 */ SOCK_TIMESTAMPING_TX_HARDWARE, /* %SOF_TIMESTAMPING_TX_HARDWARE */ SOCK_TIMESTAMPING_TX_SOFTWARE, /* %SOF_TIMESTAMPING_TX_SOFTWARE */ SOCK_TIMESTAMPING_RX_HARDWARE, /* %SOF_TIMESTAMPING_RX_HARDWARE */ @@ -563,9 +565,48 @@ static inline int sock_flag(struct sock *sk, enum sock_flags flag) return test_bit(flag, &sk->sk_flags); } +static inline int sk_has_memalloc(struct sock *sk) +{ + return sock_flag(sk, SOCK_MEMALLOC); +} + +extern struct mem_reserve net_rx_reserve; +extern struct mem_reserve net_skb_reserve; + +#ifdef CONFIG_NETVM +/* + * 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 int memalloc_socks; + +static inline int sk_memalloc_socks(void) +{ + return memalloc_socks; +} + +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); +#else +static inline int sk_memalloc_socks(void) +{ + return 0; +} + +static inline int sk_clear_memalloc(struct sock *sk) +{ + return 0; +} +#endif + 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) diff --git a/net/Kconfig b/net/Kconfig index 0d68b40..2b61a85 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -284,4 +284,7 @@ source "net/9p/Kconfig" source "net/caif/Kconfig" +config NETVM + def_bool n + endif # if NET diff --git a/net/core/sock.c b/net/core/sock.c index fef2434..6bd5765 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -111,6 +111,7 @@ #include #include #include +#include #include #include @@ -224,6 +225,105 @@ int net_cls_subsys_id = -1; EXPORT_SYMBOL_GPL(net_cls_subsys_id); #endif +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; + +#ifdef CONFIG_NETVM +static DEFINE_MUTEX(memalloc_socks_lock); +int memalloc_socks; + +/** + * 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 err; + + mutex_lock(&memalloc_socks_lock); + err = mem_reserve_pages_add(&net_tx_pages, tx_reserve_pages); + if (err) + goto unlock; + + /* + * either socks is positive and we need to check for 0 -> !0 + * transition and connect the reserve tree when we observe it. + */ + if (!memalloc_socks && socks > 0) { + err = mem_reserve_connect(&net_reserve, &mem_reserve_root); + if (err) { + /* + * if we failed to connect the tree, undo the tx + * reserve so that failure has no side effects. + */ + mem_reserve_pages_add(&net_tx_pages, -tx_reserve_pages); + goto unlock; + } + } + memalloc_socks += socks; + /* + * or socks is negative and we must observe the !0 -> 0 transition + * and disconnect the reserve tree. + */ + if (!memalloc_socks && socks) + mem_reserve_disconnect(&net_reserve); + +unlock: + mutex_unlock(&memalloc_socks_lock); + + return err; +} +EXPORT_SYMBOL_GPL(sk_adjust_memalloc); + +/** + * 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); + + 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); +#endif + static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) { struct timeval tv; @@ -1121,6 +1221,7 @@ static void __sk_free(struct sock *sk) { struct sk_filter *filter; + sk_clear_memalloc(sk); if (sk->sk_destruct) sk->sk_destruct(sk); @@ -1300,6 +1401,12 @@ 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); } /* -- 1.7.1.1 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org