From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: Linus Torvalds <torvalds@linux-foundation.org>,
Andrew Morton <akpm@linux-foundation.org>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
netdev@vger.kernel.org, trond.myklebust@fys.uio.no
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: [PATCH 15/29] netvm: network reserve infrastructure
Date: Fri, 14 Dec 2007 16:39:22 +0100 [thread overview]
Message-ID: <20071214154441.250857000@chello.nl> (raw)
In-Reply-To: 20071214153907.770251000@chello.nl
[-- Attachment #1: netvm-reserve.patch --]
[-- Type: text/plain, Size: 7304 bytes --]
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 <a.p.zijlstra@chello.nl>
---
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 <linux/skbuff.h> /* struct sk_buff */
#include <linux/mm.h>
#include <linux/security.h>
+#include <linux/reserve.h>
#include <linux/filter.h>
@@ -403,6 +404,7 @@ 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)
@@ -425,9 +427,40 @@ 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 <linux/tcp.h>
#include <linux/init.h>
#include <linux/highmem.h>
+#include <linux/reserve.h>
#include <asm/uaccess.h>
#include <asm/system.h>
@@ -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;
+struct mem_reserve net_skb_reserve;
+static struct mem_reserve net_tx_reserve;
+static struct mem_reserve net_tx_pages;
+
+EXPORT_SYMBOL_GPL(net_rx_reserve); /* modular ipv6 only */
+EXPORT_SYMBOL_GPL(net_skb_reserve); /* modular ipv6 only */
+
+/*
+ * 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;
@@ -952,6 +1058,7 @@ void sk_free(struct sock *sk)
{
struct sk_filter *filter;
+ sk_clear_memalloc(sk);
if (sk->sk_destruct)
sk->sk_destruct(sk);
@@ -1079,6 +1186,12 @@ 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
@@ -238,6 +238,9 @@ endmenu
source "net/rfkill/Kconfig"
source "net/9p/Kconfig"
+config NETVM
+ def_bool n
+
endif # if NET
endmenu # Networking
--
next prev parent reply other threads:[~2007-12-14 19:30 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-12-14 15:39 [PATCH 00/29] Swap over NFS -v15 Peter Zijlstra
2007-12-14 15:39 ` [PATCH 01/29] mm: gfp_to_alloc_flags() Peter Zijlstra
2007-12-14 15:39 ` [PATCH 02/29] mm: tag reseve pages Peter Zijlstra
2007-12-14 15:39 ` [PATCH 03/29] mm: slb: add knowledge of reserve pages Peter Zijlstra
2007-12-14 22:51 ` Daniel Phillips
2007-12-15 10:10 ` Daniel Phillips
2007-12-14 15:39 ` [PATCH 04/29] mm: kmem_estimate_pages() Peter Zijlstra
2007-12-14 22:05 ` Daniel Phillips
2007-12-14 15:39 ` [PATCH 05/29] mm: allow PF_MEMALLOC from softirq context Peter Zijlstra
2007-12-14 15:39 ` [PATCH 06/29] mm: serialize access to min_free_kbytes Peter Zijlstra
2007-12-14 15:39 ` [PATCH 07/29] mm: emergency pool Peter Zijlstra
2007-12-14 15:39 ` [PATCH 08/29] mm: system wide ALLOC_NO_WATERMARK Peter Zijlstra
2007-12-14 15:39 ` [PATCH 09/29] mm: __GFP_MEMALLOC Peter Zijlstra
2007-12-14 15:39 ` [PATCH 10/29] mm: memory reserve management Peter Zijlstra
2007-12-14 15:39 ` [PATCH 11/29] selinux: tag avc cache alloc as non-critical Peter Zijlstra
2007-12-14 15:39 ` [PATCH 12/29] net: wrap sk->sk_backlog_rcv() Peter Zijlstra
2007-12-14 15:39 ` [PATCH 13/29] net: packet split receive api Peter Zijlstra
2007-12-14 15:39 ` [PATCH 14/29] net: sk_allocation() - concentrate socket related allocations Peter Zijlstra
2007-12-14 15:39 ` Peter Zijlstra [this message]
2007-12-14 15:39 ` [PATCH 16/29] netvm: INET reserves Peter Zijlstra
2007-12-14 21:10 ` Daniel Phillips
2007-12-14 15:39 ` [PATCH 17/29] netvm: hook skb allocation to reserves Peter Zijlstra
2007-12-14 15:39 ` [PATCH 18/29] netvm: filter emergency skbs Peter Zijlstra
2007-12-14 15:39 ` [PATCH 19/29] netvm: prevent a TCP specific deadlock Peter Zijlstra
2007-12-14 15:39 ` [PATCH 20/29] netfilter: NF_QUEUE vs emergency skbs Peter Zijlstra
2007-12-14 15:39 ` [PATCH 21/29] netvm: skb processing Peter Zijlstra
2007-12-14 15:39 ` [PATCH 22/29] mm: prepare swap entry methods for use in page methods Peter Zijlstra
2007-12-14 15:39 ` [PATCH 23/29] mm: add support for non block device backed swap files Peter Zijlstra
2007-12-14 15:39 ` [PATCH 24/29] mm: methods for teaching filesystems about PG_swapcache pages Peter Zijlstra
2007-12-14 15:39 ` [PATCH 25/29] nfs: remove mempools Peter Zijlstra
2007-12-14 15:39 ` [PATCH 26/29] nfs: teach the NFS client how to treat PG_swapcache pages Peter Zijlstra
2007-12-14 15:39 ` [PATCH 27/29] nfs: disable data cache revalidation for swapfiles Peter Zijlstra
2007-12-14 15:39 ` [PATCH 28/29] nfs: enable swap on NFS Peter Zijlstra
2007-12-14 15:39 ` [PATCH 29/29] nfs: fix various memory recursions possible with swap over NFS Peter Zijlstra
2007-12-14 21:07 ` [PATCH 00/29] Swap over NFS -v15 Daniel Phillips
2007-12-19 22:22 ` Bill Davidsen
2007-12-20 8:00 ` Peter Zijlstra
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20071214154441.250857000@chello.nl \
--to=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=netdev@vger.kernel.org \
--cc=torvalds@linux-foundation.org \
--cc=trond.myklebust@fys.uio.no \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).