* [PATCH 07/33] mm: serialize access to min_free_kbytes
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: mm-setup_per_zone_pages_min.patch --]
[-- Type: text/plain, Size: 1835 bytes --]
There is a small race between the procfs caller and the memory hotplug caller
of setup_per_zone_pages_min(). Not a big deal, but the next patch will add yet
another caller. Time to close the gap.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
mm/page_alloc.c | 16 +++++++++++++---
1 file changed, 13 insertions(+), 3 deletions(-)
Index: linux-2.6/mm/page_alloc.c
===================================================================
--- linux-2.6.orig/mm/page_alloc.c
+++ linux-2.6/mm/page_alloc.c
@@ -116,6 +116,7 @@ static char * const zone_names[MAX_NR_ZO
"Movable",
};
+static DEFINE_SPINLOCK(min_free_lock);
int min_free_kbytes = 1024;
unsigned long __meminitdata nr_kernel_pages;
@@ -4162,12 +4163,12 @@ static void setup_per_zone_lowmem_reserv
}
/**
- * setup_per_zone_pages_min - called when min_free_kbytes changes.
+ * __setup_per_zone_pages_min - called when min_free_kbytes changes.
*
* Ensures that the pages_{min,low,high} values for each zone are set correctly
* with respect to min_free_kbytes.
*/
-void setup_per_zone_pages_min(void)
+static void __setup_per_zone_pages_min(void)
{
unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
unsigned long lowmem_pages = 0;
@@ -4222,6 +4223,15 @@ void setup_per_zone_pages_min(void)
calculate_totalreserve_pages();
}
+void setup_per_zone_pages_min(void)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&min_free_lock, flags);
+ __setup_per_zone_pages_min();
+ spin_unlock_irqrestore(&min_free_lock, flags);
+}
+
/*
* Initialise min_free_kbytes.
*
@@ -4257,7 +4267,7 @@ static int __init init_per_zone_pages_mi
min_free_kbytes = 128;
if (min_free_kbytes > 65536)
min_free_kbytes = 65536;
- setup_per_zone_pages_min();
+ __setup_per_zone_pages_min();
setup_per_zone_lowmem_reserve();
return 0;
}
--
^ permalink raw reply
* [PATCH 09/33] mm: system wide ALLOC_NO_WATERMARK
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: global-ALLOC_NO_WATERMARKS.patch --]
[-- Type: text/plain, Size: 852 bytes --]
Change ALLOC_NO_WATERMARK page allocation such that the reserves are system
wide - which they are per setup_per_zone_pages_min(), when we scrape the
barrel, do it properly.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
mm/page_alloc.c | 6 ++++++
1 file changed, 6 insertions(+)
Index: linux-2.6/mm/page_alloc.c
===================================================================
--- linux-2.6.orig/mm/page_alloc.c
+++ linux-2.6/mm/page_alloc.c
@@ -1638,6 +1638,12 @@ restart:
rebalance:
if (alloc_flags & ALLOC_NO_WATERMARKS) {
nofail_alloc:
+ /*
+ * break out of mempolicy boundaries
+ */
+ zonelist = NODE_DATA(numa_node_id())->node_zonelists +
+ gfp_zone(gfp_mask);
+
/* go through the zonelist yet again, ignoring mins */
page = get_page_from_freelist(gfp_mask, order, zonelist,
ALLOC_NO_WATERMARKS);
--
^ permalink raw reply
* [PATCH 11/33] mm: memory reserve management
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: mm-reserve.patch --]
[-- Type: text/plain, Size: 14253 bytes --]
Generic reserve management code.
It provides methods to reserve and charge. Upon this, generic alloc/free style
reserve pools could be build, which could fully replace mempool_t
functionality.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
include/linux/reserve.h | 54 +++++
mm/Makefile | 2
mm/reserve.c | 436 ++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 491 insertions(+), 1 deletion(-)
Index: linux-2.6/include/linux/reserve.h
===================================================================
--- /dev/null
+++ linux-2.6/include/linux/reserve.h
@@ -0,0 +1,54 @@
+/*
+ * Memory reserve management.
+ *
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *
+ * This file contains the public data structure and API definitions.
+ */
+
+#ifndef _LINUX_RESERVE_H
+#define _LINUX_RESERVE_H
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
+struct mem_reserve {
+ struct mem_reserve *parent;
+ struct list_head children;
+ struct list_head siblings;
+
+ const char *name;
+
+ long pages;
+ long limit;
+ long usage;
+ spinlock_t lock; /* protects limit and usage */
+};
+
+extern struct mem_reserve mem_reserve_root;
+
+void mem_reserve_init(struct mem_reserve *res, const char *name,
+ struct mem_reserve *parent);
+int mem_reserve_connect(struct mem_reserve *new_child,
+ struct mem_reserve *node);
+int mem_reserve_disconnect(struct mem_reserve *node);
+
+int mem_reserve_pages_set(struct mem_reserve *res, long pages);
+int mem_reserve_pages_add(struct mem_reserve *res, long pages);
+int mem_reserve_pages_charge(struct mem_reserve *res, long pages,
+ int overcommit);
+
+int mem_reserve_kmalloc_set(struct mem_reserve *res, long bytes);
+int mem_reserve_kmalloc_charge(struct mem_reserve *res, long bytes,
+ int overcommit);
+
+struct kmem_cache;
+
+int mem_reserve_kmem_cache_set(struct mem_reserve *res,
+ struct kmem_cache *s,
+ int objects);
+int mem_reserve_kmem_cache_charge(struct mem_reserve *res,
+ long objs,
+ int overcommit);
+
+#endif /* _LINUX_RESERVE_H */
Index: linux-2.6/mm/Makefile
===================================================================
--- linux-2.6.orig/mm/Makefile
+++ linux-2.6/mm/Makefile
@@ -11,7 +11,7 @@ obj-y := bootmem.o filemap.o mempool.o
page_alloc.o page-writeback.o pdflush.o \
readahead.o swap.o truncate.o vmscan.o \
prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
- page_isolation.o $(mmu-y)
+ page_isolation.o reserve.o $(mmu-y)
obj-$(CONFIG_BOUNCE) += bounce.o
obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o thrash.o
Index: linux-2.6/mm/reserve.c
===================================================================
--- /dev/null
+++ linux-2.6/mm/reserve.c
@@ -0,0 +1,436 @@
+/*
+ * Memory reserve management.
+ *
+ * Copyright (C) 2007, Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *
+ * Description:
+ *
+ * Manage a set of memory reserves.
+ *
+ * A memory reserve is a reserve for a specified number of object of specified
+ * size. Since memory is managed in pages, this reserve demand is then
+ * translated into a page unit.
+ *
+ * So each reserve has a specified object limit, an object usage count and a
+ * number of pages required to back these objects.
+ *
+ * Usage is charged against a reserve, if the charge fails, the resource must
+ * not be allocated/used.
+ *
+ * The reserves are managed in a tree, and the resource demands (pages and
+ * limit) are propagated up the tree. Obviously the object limit will be
+ * meaningless as soon as the unit starts mixing, but the required page reserve
+ * (being of one unit) is still valid at the root.
+ *
+ * It is the page demand of the root node that is used to set the global
+ * reserve (adjust_memalloc_reserve() which sets zone->pages_emerg).
+ *
+ * As long as a subtree has the same usage unit, an aggregate node can be used
+ * to charge against, instead of the leaf nodes. However, do be consistent with
+ * who is charged, resource usage is not propagated up the tree (for
+ * performance reasons).
+ */
+
+#include <linux/reserve.h>
+#include <linux/mutex.h>
+#include <linux/mmzone.h>
+#include <linux/log2.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+static DEFINE_MUTEX(mem_reserve_mutex);
+
+/**
+ * @mem_reserve_root - the global reserve root
+ *
+ * The global reserve is empty, and has no limit unit, it merely
+ * acts as an aggregation point for reserves and an interface to
+ * adjust_memalloc_reserve().
+ */
+struct mem_reserve mem_reserve_root = {
+ .children = LIST_HEAD_INIT(mem_reserve_root.children),
+ .siblings = LIST_HEAD_INIT(mem_reserve_root.siblings),
+ .name = "total reserve",
+};
+
+EXPORT_SYMBOL_GPL(mem_reserve_root);
+
+/**
+ * mem_reserve_init - initialize a memory reserve object
+ * @res - the new reserve object
+ * @name - a name for this reserve
+ */
+void mem_reserve_init(struct mem_reserve *res, const char *name,
+ struct mem_reserve *parent)
+{
+ memset(res, 0, sizeof(*res));
+ INIT_LIST_HEAD(&res->children);
+ INIT_LIST_HEAD(&res->siblings);
+ res->name = name;
+
+ if (parent)
+ mem_reserve_connect(res, parent);
+}
+
+EXPORT_SYMBOL_GPL(mem_reserve_init);
+
+/*
+ * propagate the pages and limit changes up the tree.
+ */
+static void __calc_reserve(struct mem_reserve *res, long pages, long limit)
+{
+ unsigned long flags;
+
+ for ( ; res; res = res->parent) {
+ res->pages += pages;
+
+ if (limit) {
+ spin_lock_irqsave(&res->lock, flags);
+ res->limit += limit;
+ spin_unlock_irqrestore(&res->lock, flags);
+ }
+ }
+}
+
+/**
+ * __mem_reserve_add - primitive to change the size of a reserve
+ * @res - reserve to change
+ * @pages - page delta
+ * @limit - usage limit delta
+ *
+ * Returns -ENOMEM when a size increase is not possible atm.
+ */
+static int __mem_reserve_add(struct mem_reserve *res, long pages, long limit)
+{
+ int ret = 0;
+ long reserve;
+
+ reserve = mem_reserve_root.pages;
+ __calc_reserve(res, pages, 0);
+ reserve = mem_reserve_root.pages - reserve;
+
+ if (reserve) {
+ ret = adjust_memalloc_reserve(reserve);
+ if (ret)
+ __calc_reserve(res, -pages, 0);
+ }
+
+ if (!ret)
+ __calc_reserve(res, 0, limit);
+
+ return ret;
+}
+
+/**
+ * __mem_reserve_charge - primitive to charge object usage to a reserve
+ * @res - reserve to charge
+ * @charge - size of the charge
+ * @overcommit - allow despite of limit (use with caution!)
+ *
+ * Returns non-zero on success, zero on failure.
+ */
+static
+int __mem_reserve_charge(struct mem_reserve *res, long charge, int overcommit)
+{
+ unsigned long flags;
+ int ret = 0;
+
+ spin_lock_irqsave(&res->lock, flags);
+ if (charge < 0 || res->usage + charge < res->limit || overcommit) {
+ res->usage += charge;
+ if (unlikely(res->usage < 0))
+ res->usage = 0;
+ ret = 1;
+ }
+ spin_unlock_irqrestore(&res->lock, flags);
+
+ return ret;
+}
+
+/**
+ * mem_reserve_connect - connect a reserve to another in a child-parent relation
+ * @new_child - the reserve node to connect (child)
+ * @node - the reserve node to connect to (parent)
+ *
+ * Returns -ENOMEM when the new connection would increase the reserve (parent
+ * is connected to mem_reserve_root) and there is no memory to do so.
+ *
+ * The child is _NOT_ connected on error.
+ */
+int mem_reserve_connect(struct mem_reserve *new_child, struct mem_reserve *node)
+{
+ int ret;
+
+ WARN_ON(!new_child->name);
+
+ mutex_lock(&mem_reserve_mutex);
+ new_child->parent = node;
+ list_add(&new_child->siblings, &node->children);
+ ret = __mem_reserve_add(node, new_child->pages, new_child->limit);
+ if (ret) {
+ new_child->parent = NULL;
+ list_del_init(&new_child->siblings);
+ }
+ mutex_unlock(&mem_reserve_mutex);
+
+ return ret;
+}
+
+EXPORT_SYMBOL_GPL(mem_reserve_connect);
+
+/**
+ * mem_reserve_disconnect - sever a nodes connection to the reserve tree
+ * @node - the node to disconnect
+ *
+ * Could, in theory, return -ENOMEM, but since disconnecting a node _should_
+ * only decrease the reserves that _should_ not happen.
+ */
+int mem_reserve_disconnect(struct mem_reserve *node)
+{
+ int ret;
+
+ BUG_ON(!node->parent);
+
+ mutex_lock(&mem_reserve_mutex);
+ ret = __mem_reserve_add(node->parent, -node->pages, -node->limit);
+ if (!ret) {
+ node->parent = NULL;
+ list_del_init(&node->siblings);
+ }
+ mutex_unlock(&mem_reserve_mutex);
+
+ return ret;
+}
+
+EXPORT_SYMBOL_GPL(mem_reserve_disconnect);
+
+#ifdef CONFIG_PROC_FS
+
+/*
+ * Simple output of the reserve tree in: /proc/reserve_info
+ * Example:
+ *
+ * localhost ~ # cat /proc/reserve_info
+ * total reserve 8156K (0/544817)
+ * total network reserve 8156K (0/544817)
+ * network TX reserve 196K (0/49)
+ * protocol TX pages 196K (0/49)
+ * network RX reserve 7960K (0/544768)
+ * IPv6 route cache 1372K (0/4096)
+ * IPv4 route cache 5468K (0/16384)
+ * SKB data reserve 1120K (0/524288)
+ * IPv6 fragment cache 560K (0/262144)
+ * IPv4 fragment cache 560K (0/262144)
+ */
+
+static void mem_reserve_show_item(struct seq_file *m, struct mem_reserve *res,
+ int nesting)
+{
+ int i;
+ struct mem_reserve *child;
+
+ for (i = 0; i < nesting; i++)
+ seq_puts(m, " ");
+
+ seq_printf(m, "%-30s %ldK (%ld/%ld)\n",
+ res->name, res->pages << (PAGE_SHIFT - 10),
+ res->usage, res->limit);
+
+ list_for_each_entry(child, &res->children, siblings)
+ mem_reserve_show_item(m, child, nesting+1);
+}
+
+static int mem_reserve_show(struct seq_file *m, void *v)
+{
+ mutex_lock(&mem_reserve_mutex);
+ mem_reserve_show_item(m, &mem_reserve_root, 0);
+ mutex_unlock(&mem_reserve_mutex);
+
+ return 0;
+}
+
+static int mem_reserve_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, mem_reserve_show, NULL);
+}
+
+static const struct file_operations mem_reserve_opterations = {
+ .open = mem_reserve_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static __init int mem_reserve_proc_init(void)
+{
+ struct proc_dir_entry *entry;
+
+ entry = create_proc_entry("reserve_info", S_IRUSR, NULL);
+ if (entry)
+ entry->proc_fops = &mem_reserve_opterations;
+
+ return 0;
+}
+
+__initcall(mem_reserve_proc_init);
+
+#endif
+
+/*
+ * alloc_page helpers
+ */
+
+/**
+ * mem_reserve_pages_set - set reserves size in pages
+ * @res - reserve to set
+ * @pages - size in pages to set it to
+ *
+ * Returns -ENOMEM when it fails to set the reserve. On failure the old size
+ * is preserved.
+ */
+int mem_reserve_pages_set(struct mem_reserve *res, long pages)
+{
+ int ret;
+
+ mutex_lock(&mem_reserve_mutex);
+ pages -= res->pages;
+ ret = __mem_reserve_add(res, pages, pages);
+ mutex_unlock(&mem_reserve_mutex);
+
+ return ret;
+}
+
+EXPORT_SYMBOL_GPL(mem_reserve_pages_set);
+
+/**
+ * mem_reserve_pages_add - change the size in a relative way
+ * @res - reserve to change
+ * @pages - number of pages to add (or subtract when negative)
+ *
+ * Similar to mem_reserve_pages_set, except that the argument is relative instead
+ * of absolute.
+ *
+ * Returns -ENOMEM when it fails to increase.
+ */
+int mem_reserve_pages_add(struct mem_reserve *res, long pages)
+{
+ int ret;
+
+ mutex_lock(&mem_reserve_mutex);
+ ret = __mem_reserve_add(res, pages, pages);
+ mutex_unlock(&mem_reserve_mutex);
+
+ return ret;
+}
+
+/**
+ * mem_reserve_pages_charge - charge page usage to a reserve
+ * @res - reserve to charge
+ * @pages - size to charge
+ * @overcommit - disregard the usage limit (use with caution!)
+ *
+ * Returns non-zero on success.
+ */
+int mem_reserve_pages_charge(struct mem_reserve *res, long pages, int overcommit)
+{
+ return __mem_reserve_charge(res, pages, overcommit);
+}
+
+EXPORT_SYMBOL_GPL(mem_reserve_pages_charge);
+
+/*
+ * kmalloc helpers
+ */
+
+/**
+ * mem_reserve_kmalloc_set - set this reserve to bytes worth of kmalloc
+ * @res - reserve to change
+ * @bytes - size in bytes to reserve
+ *
+ * Returns -ENOMEM on failure.
+ */
+int mem_reserve_kmalloc_set(struct mem_reserve *res, long bytes)
+{
+ int ret;
+ long pages;
+
+ mutex_lock(&mem_reserve_mutex);
+ pages = kestimate(GFP_ATOMIC, bytes);
+ pages -= res->pages;
+ bytes -= res->limit;
+ ret = __mem_reserve_add(res, pages, bytes);
+ mutex_unlock(&mem_reserve_mutex);
+
+ return ret;
+}
+
+EXPORT_SYMBOL_GPL(mem_reserve_kmalloc_set);
+
+/**
+ * mem_reserve_kmalloc_charge - charge bytes to a reserve
+ * @res - reserve to charge
+ * @bytes - bytes to charge
+ * @overcommit - disregard the usage limit (use with caution!)
+ *
+ * Returns non-zero on success.
+ */
+int mem_reserve_kmalloc_charge(struct mem_reserve *res, long bytes,
+ int overcommit)
+{
+ if (bytes < 0)
+ bytes = -roundup_pow_of_two(-bytes);
+ else
+ bytes = roundup_pow_of_two(bytes);
+
+ return __mem_reserve_charge(res, bytes, overcommit);
+}
+
+EXPORT_SYMBOL_GPL(mem_reserve_kmalloc_charge);
+
+/*
+ * kmem_cache helpers
+ */
+
+/**
+ * mem_reserve_kmem_cache_set - set reserve to @objects worth of kmem_cache_alloc of @s
+ * @res - reserve to set
+ * @s - kmem_cache to reserve from
+ * @objects - number of objects to reserve
+ *
+ * Returns -ENOMEM on failure.
+ */
+int mem_reserve_kmem_cache_set(struct mem_reserve *res, struct kmem_cache *s,
+ int objects)
+{
+ int ret;
+ long pages;
+
+ mutex_lock(&mem_reserve_mutex);
+ pages = kmem_estimate_pages(s, GFP_ATOMIC, objects);
+ pages -= res->pages;
+ objects -= res->limit;
+ ret = __mem_reserve_add(res, pages, objects);
+ mutex_unlock(&mem_reserve_mutex);
+
+ return ret;
+}
+
+EXPORT_SYMBOL_GPL(mem_reserve_kmem_cache_set);
+
+/**
+ * mem_reserve_kmem_cache_charge - charge (or uncharge) usage of objs
+ * @res - reserve to charge
+ * @objs - objects to charge for
+ * @overcommit - disregard the usage limit (use with caution!)
+ *
+ * Returns non-zero on success.
+ */
+int mem_reserve_kmem_cache_charge(struct mem_reserve *res, long objs,
+ int overcommit)
+{
+ return __mem_reserve_charge(res, objs, overcommit);
+}
+
+EXPORT_SYMBOL_GPL(mem_reserve_kmem_cache_charge);
--
^ permalink raw reply
* [PATCH 12/33] selinux: tag avc cache alloc as non-critical
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra, James Morris
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: mm-selinux-emergency.patch --]
[-- Type: text/plain, Size: 773 bytes --]
Failing to allocate a cache entry will only harm performance not correctness.
Do not consume valuable reserve pages for something like that.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: James Morris <jmorris@namei.org>
---
security/selinux/avc.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
Index: linux-2.6-2/security/selinux/avc.c
===================================================================
--- linux-2.6-2.orig/security/selinux/avc.c
+++ linux-2.6-2/security/selinux/avc.c
@@ -334,7 +334,7 @@ static struct avc_node *avc_alloc_node(v
{
struct avc_node *node;
- node = kmem_cache_zalloc(avc_node_cachep, GFP_ATOMIC);
+ node = kmem_cache_zalloc(avc_node_cachep, GFP_ATOMIC|__GFP_NOMEMALLOC);
if (!node)
goto out;
--
^ permalink raw reply
* [PATCH 15/33] net: sk_allocation() - concentrate socket related allocations
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: net-sk_allocation.patch --]
[-- Type: text/plain, Size: 5034 bytes --]
Introduce sk_allocation(), this function allows to inject sock specific
flags to each sock related allocation.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
include/net/sock.h | 7 ++++++-
net/ipv4/tcp_output.c | 11 ++++++-----
net/ipv6/tcp_ipv6.c | 14 +++++++++-----
3 files changed, 21 insertions(+), 11 deletions(-)
Index: linux-2.6/net/ipv4/tcp_output.c
===================================================================
--- linux-2.6.orig/net/ipv4/tcp_output.c
+++ linux-2.6/net/ipv4/tcp_output.c
@@ -2081,7 +2081,7 @@ void tcp_send_fin(struct sock *sk)
} else {
/* Socket is locked, keep trying until memory is available. */
for (;;) {
- skb = alloc_skb_fclone(MAX_TCP_HEADER, GFP_KERNEL);
+ skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
if (skb)
break;
yield();
@@ -2114,7 +2114,7 @@ void tcp_send_active_reset(struct sock *
struct sk_buff *skb;
/* NOTE: No TCP options attached and we never retransmit this. */
- skb = alloc_skb(MAX_TCP_HEADER, priority);
+ skb = alloc_skb(MAX_TCP_HEADER, sk_allocation(sk, priority));
if (!skb) {
NET_INC_STATS(LINUX_MIB_TCPABORTFAILED);
return;
@@ -2187,7 +2187,8 @@ struct sk_buff * tcp_make_synack(struct
__u8 *md5_hash_location;
#endif
- skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC);
+ skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1,
+ sk_allocation(sk, GFP_ATOMIC));
if (skb == NULL)
return NULL;
@@ -2446,7 +2447,7 @@ void tcp_send_ack(struct sock *sk)
* tcp_transmit_skb() will set the ownership to this
* sock.
*/
- buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
+ buff = alloc_skb(MAX_TCP_HEADER, sk_allocation(sk, GFP_ATOMIC));
if (buff == NULL) {
inet_csk_schedule_ack(sk);
inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
@@ -2488,7 +2489,7 @@ static int tcp_xmit_probe_skb(struct soc
struct sk_buff *skb;
/* We don't queue it, tcp_transmit_skb() sets ownership. */
- skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
+ skb = alloc_skb(MAX_TCP_HEADER, sk_allocation(sk, GFP_ATOMIC));
if (skb == NULL)
return -1;
Index: linux-2.6/include/net/sock.h
===================================================================
--- linux-2.6.orig/include/net/sock.h
+++ linux-2.6/include/net/sock.h
@@ -419,6 +419,11 @@ static inline int sock_flag(struct sock
return test_bit(flag, &sk->sk_flags);
}
+static inline gfp_t sk_allocation(struct sock *sk, gfp_t gfp_mask)
+{
+ return gfp_mask;
+}
+
static inline void sk_acceptq_removed(struct sock *sk)
{
sk->sk_ack_backlog--;
@@ -1212,7 +1217,7 @@ static inline struct sk_buff *sk_stream_
int hdr_len;
hdr_len = SKB_DATA_ALIGN(sk->sk_prot->max_header);
- skb = alloc_skb_fclone(size + hdr_len, gfp);
+ skb = alloc_skb_fclone(size + hdr_len, sk_allocation(sk, gfp));
if (skb) {
skb->truesize += mem;
if (sk_stream_wmem_schedule(sk, skb->truesize)) {
Index: linux-2.6/net/ipv6/tcp_ipv6.c
===================================================================
--- linux-2.6.orig/net/ipv6/tcp_ipv6.c
+++ linux-2.6/net/ipv6/tcp_ipv6.c
@@ -573,7 +573,8 @@ static int tcp_v6_md5_do_add(struct sock
} else {
/* reallocate new list if current one is full. */
if (!tp->md5sig_info) {
- tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info), GFP_ATOMIC);
+ tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info),
+ sk_allocation(sk, GFP_ATOMIC));
if (!tp->md5sig_info) {
kfree(newkey);
return -ENOMEM;
@@ -583,7 +584,8 @@ static int tcp_v6_md5_do_add(struct sock
tcp_alloc_md5sig_pool();
if (tp->md5sig_info->alloced6 == tp->md5sig_info->entries6) {
keys = kmalloc((sizeof (tp->md5sig_info->keys6[0]) *
- (tp->md5sig_info->entries6 + 1)), GFP_ATOMIC);
+ (tp->md5sig_info->entries6 + 1)),
+ sk_allocation(sk, GFP_ATOMIC));
if (!keys) {
tcp_free_md5sig_pool();
@@ -709,7 +711,7 @@ static int tcp_v6_parse_md5_keys (struct
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_md5sig_info *p;
- p = kzalloc(sizeof(struct tcp_md5sig_info), GFP_KERNEL);
+ p = kzalloc(sizeof(struct tcp_md5sig_info), sk->sk_allocation);
if (!p)
return -ENOMEM;
@@ -1006,7 +1008,7 @@ static void tcp_v6_send_reset(struct soc
*/
buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len,
- GFP_ATOMIC);
+ sk_allocation(sk, GFP_ATOMIC));
if (buff == NULL)
return;
@@ -1085,10 +1087,12 @@ static void tcp_v6_send_ack(struct tcp_t
struct tcp_md5sig_key *key;
struct tcp_md5sig_key tw_key;
#endif
+ gfp_t gfp_mask = GFP_ATOMIC;
#ifdef CONFIG_TCP_MD5SIG
if (!tw && skb->sk) {
key = tcp_v6_md5_do_lookup(skb->sk, &ipv6_hdr(skb)->daddr);
+ gfp_mask = sk_allocation(skb->sk, gfp_mask);
} else if (tw && tw->tw_md5_keylen) {
tw_key.key = tw->tw_md5_key;
tw_key.keylen = tw->tw_md5_keylen;
@@ -1106,7 +1110,7 @@ static void tcp_v6_send_ack(struct tcp_t
#endif
buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len,
- GFP_ATOMIC);
+ gfp_mask);
if (buff == NULL)
return;
--
^ permalink raw reply
* [PATCH 18/33] netvm: INET reserves.
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: netvm-reserve-inet.patch --]
[-- Type: text/plain, Size: 12064 bytes --]
Add reserves for INET.
The two big users seem to be the route cache and ip-fragment cache.
Reserve the route cache under generic RX reserve, its usage is bounded by
the high reclaim watermark, and thus does not need further accounting.
Reserve the ip-fragement caches under SKB data reserve, these add to the
SKB RX limit. By ensuring we can at least receive as much data as fits in
the reassmbly line we avoid fragment attack deadlocks.
Use proc conv() routines to update these limits and return -ENOMEM to user
space.
Adds to the reserve tree:
total network reserve
network TX reserve
protocol TX pages
network RX reserve
+ IPv6 route cache
+ IPv4 route cache
SKB data reserve
+ IPv6 fragment cache
+ IPv4 fragment cache
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
include/linux/sysctl.h | 11 +++++++++++
kernel/sysctl.c | 8 ++++++--
net/ipv4/ip_fragment.c | 7 +++++++
net/ipv4/route.c | 30 +++++++++++++++++++++++++++++-
net/ipv4/sysctl_net_ipv4.c | 24 +++++++++++++++++++++++-
net/ipv6/reassembly.c | 7 +++++++
net/ipv6/route.c | 31 ++++++++++++++++++++++++++++++-
net/ipv6/sysctl_net_ipv6.c | 24 +++++++++++++++++++++++-
8 files changed, 136 insertions(+), 6 deletions(-)
Index: linux-2.6/net/ipv4/sysctl_net_ipv4.c
===================================================================
--- linux-2.6.orig/net/ipv4/sysctl_net_ipv4.c
+++ linux-2.6/net/ipv4/sysctl_net_ipv4.c
@@ -18,6 +18,7 @@
#include <net/route.h>
#include <net/tcp.h>
#include <net/cipso_ipv4.h>
+#include <linux/reserve.h>
/* From af_inet.c */
extern int sysctl_ip_nonlocal_bind;
@@ -186,6 +187,27 @@ static int strategy_allowed_congestion_c
}
+extern struct mem_reserve ipv4_frag_reserve;
+
+static int do_proc_dointvec_fragment_conv(int *negp, unsigned long *lvalp,
+ int *valp, int write, void *data)
+{
+ if (write) {
+ long value = *negp ? -*lvalp : *lvalp;
+ int err = mem_reserve_kmalloc_set(&ipv4_frag_reserve, value);
+ if (err)
+ return err;
+ }
+ return do_proc_dointvec_conv(negp, lvalp, valp, write, data);
+}
+
+static int proc_dointvec_fragment(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return do_proc_dointvec(table, write, filp, buffer, lenp, ppos,
+ do_proc_dointvec_fragment_conv, NULL);
+}
+
ctl_table ipv4_table[] = {
{
.ctl_name = NET_IPV4_TCP_TIMESTAMPS,
@@ -291,7 +313,7 @@ ctl_table ipv4_table[] = {
.data = &sysctl_ipfrag_high_thresh,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec
+ .proc_handler = &proc_dointvec_fragment
},
{
.ctl_name = NET_IPV4_IPFRAG_LOW_THRESH,
Index: linux-2.6/net/ipv6/sysctl_net_ipv6.c
===================================================================
--- linux-2.6.orig/net/ipv6/sysctl_net_ipv6.c
+++ linux-2.6/net/ipv6/sysctl_net_ipv6.c
@@ -12,9 +12,31 @@
#include <net/ndisc.h>
#include <net/ipv6.h>
#include <net/addrconf.h>
+#include <linux/reserve.h>
#ifdef CONFIG_SYSCTL
+extern struct mem_reserve ipv6_frag_reserve;
+
+static int do_proc_dointvec_fragment_conv(int *negp, unsigned long *lvalp,
+ int *valp, int write, void *data)
+{
+ if (write) {
+ long value = *negp ? -*lvalp : *lvalp;
+ int err = mem_reserve_kmalloc_set(&ipv6_frag_reserve, value);
+ if (err)
+ return err;
+ }
+ return do_proc_dointvec_conv(negp, lvalp, valp, write, data);
+}
+
+static int proc_dointvec_fragment(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return do_proc_dointvec(table, write, filp, buffer, lenp, ppos,
+ do_proc_dointvec_fragment_conv, NULL);
+}
+
static ctl_table ipv6_table[] = {
{
.ctl_name = NET_IPV6_ROUTE,
@@ -44,7 +66,7 @@ static ctl_table ipv6_table[] = {
.data = &sysctl_ip6frag_high_thresh,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec
+ .proc_handler = &proc_dointvec_fragment
},
{
.ctl_name = NET_IPV6_IP6FRAG_LOW_THRESH,
Index: linux-2.6/net/ipv4/ip_fragment.c
===================================================================
--- linux-2.6.orig/net/ipv4/ip_fragment.c
+++ linux-2.6/net/ipv4/ip_fragment.c
@@ -43,6 +43,7 @@
#include <linux/udp.h>
#include <linux/inet.h>
#include <linux/netfilter_ipv4.h>
+#include <linux/reserve.h>
/* NOTE. Logic of IP defragmentation is parallel to corresponding IPv6
* code now. If you change something here, _PLEASE_ update ipv6/reassembly.c
@@ -733,6 +734,8 @@ struct sk_buff *ip_defrag(struct sk_buff
return NULL;
}
+struct mem_reserve ipv4_frag_reserve;
+
void __init ipfrag_init(void)
{
ipfrag_hash_rnd = (u32) ((num_physpages ^ (num_physpages>>7)) ^
@@ -742,6 +745,10 @@ void __init ipfrag_init(void)
ipfrag_secret_timer.function = ipfrag_secret_rebuild;
ipfrag_secret_timer.expires = jiffies + sysctl_ipfrag_secret_interval;
add_timer(&ipfrag_secret_timer);
+
+ mem_reserve_init(&ipv4_frag_reserve, "IPv4 fragment cache",
+ &net_skb_reserve);
+ mem_reserve_kmalloc_set(&ipv4_frag_reserve, sysctl_ipfrag_high_thresh);
}
EXPORT_SYMBOL(ip_defrag);
Index: linux-2.6/net/ipv6/reassembly.c
===================================================================
--- linux-2.6.orig/net/ipv6/reassembly.c
+++ linux-2.6/net/ipv6/reassembly.c
@@ -42,6 +42,7 @@
#include <linux/icmpv6.h>
#include <linux/random.h>
#include <linux/jhash.h>
+#include <linux/reserve.h>
#include <net/sock.h>
#include <net/snmp.h>
@@ -770,6 +771,8 @@ static struct inet6_protocol frag_protoc
.flags = INET6_PROTO_NOPOLICY,
};
+struct mem_reserve ipv6_frag_reserve;
+
void __init ipv6_frag_init(void)
{
if (inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT) < 0)
@@ -782,4 +785,8 @@ void __init ipv6_frag_init(void)
ip6_frag_secret_timer.function = ip6_frag_secret_rebuild;
ip6_frag_secret_timer.expires = jiffies + sysctl_ip6frag_secret_interval;
add_timer(&ip6_frag_secret_timer);
+
+ mem_reserve_init(&ipv6_frag_reserve, "IPv6 fragment cache",
+ &net_skb_reserve);
+ mem_reserve_kmalloc_set(&ipv6_frag_reserve, sysctl_ip6frag_high_thresh);
}
Index: linux-2.6/net/ipv4/route.c
===================================================================
--- linux-2.6.orig/net/ipv4/route.c
+++ linux-2.6/net/ipv4/route.c
@@ -108,6 +108,7 @@
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
+#include <linux/reserve.h>
#define RT_FL_TOS(oldflp) \
((u32)(oldflp->fl4_tos & (IPTOS_RT_MASK | RTO_ONLINK)))
@@ -2698,6 +2699,28 @@ static int ipv4_sysctl_rtcache_flush_str
return 0;
}
+static struct mem_reserve ipv4_route_reserve;
+
+static int do_proc_dointvec_route_conv(int *negp, unsigned long *lvalp,
+ int *valp, int write, void *data)
+{
+ if (write) {
+ long value = *negp ? -*lvalp : *lvalp;
+ int err = mem_reserve_kmem_cache_set(&ipv4_route_reserve,
+ ipv4_dst_ops.kmem_cachep, value);
+ if (err)
+ return err;
+ }
+ return do_proc_dointvec_conv(negp, lvalp, valp, write, data);
+}
+
+static int proc_dointvec_route(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return do_proc_dointvec(table, write, filp, buffer, lenp, ppos,
+ do_proc_dointvec_route_conv, NULL);
+}
+
ctl_table ipv4_route_table[] = {
{
.ctl_name = NET_IPV4_ROUTE_FLUSH,
@@ -2740,7 +2763,7 @@ ctl_table ipv4_route_table[] = {
.data = &ip_rt_max_size,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_dointvec_route,
},
{
/* Deprecated. Use gc_min_interval_ms */
@@ -2970,6 +2993,11 @@ int __init ip_rt_init(void)
ipv4_dst_ops.gc_thresh = (rt_hash_mask + 1);
ip_rt_max_size = (rt_hash_mask + 1) * 16;
+ mem_reserve_init(&ipv4_route_reserve, "IPv4 route cache",
+ &net_rx_reserve);
+ mem_reserve_kmem_cache_set(&ipv4_route_reserve,
+ ipv4_dst_ops.kmem_cachep, ip_rt_max_size);
+
devinet_init();
ip_fib_init();
Index: linux-2.6/net/ipv6/route.c
===================================================================
--- linux-2.6.orig/net/ipv6/route.c
+++ linux-2.6/net/ipv6/route.c
@@ -38,6 +38,7 @@
#include <linux/in6.h>
#include <linux/init.h>
#include <linux/if_arp.h>
+#include <linux/reserve.h>
#ifdef CONFIG_PROC_FS
#include <linux/proc_fs.h>
@@ -2454,6 +2455,28 @@ int ipv6_sysctl_rtcache_flush(ctl_table
return -EINVAL;
}
+static struct mem_reserve ipv6_route_reserve;
+
+static int do_proc_dointvec_route6_conv(int *negp, unsigned long *lvalp,
+ int *valp, int write, void *data)
+{
+ if (write) {
+ long value = *negp ? -*lvalp : *lvalp;
+ int err = mem_reserve_kmem_cache_set(&ipv6_route_reserve,
+ ip6_dst_ops.kmem_cachep, value);
+ if (err)
+ return err;
+ }
+ return do_proc_dointvec_conv(negp, lvalp, valp, write, data);
+}
+
+static int proc_dointvec_route6(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return do_proc_dointvec(table, write, filp, buffer, lenp, ppos,
+ do_proc_dointvec_route6_conv, NULL);
+}
+
ctl_table ipv6_route_table[] = {
{
.procname = "flush",
@@ -2476,7 +2499,7 @@ ctl_table ipv6_route_table[] = {
.data = &ip6_rt_max_size,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec,
+ .proc_handler = &proc_dointvec_route6,
},
{
.ctl_name = NET_IPV6_ROUTE_GC_MIN_INTERVAL,
@@ -2564,6 +2587,12 @@ void __init ip6_route_init(void)
proc_net_fops_create(&init_net, "rt6_stats", S_IRUGO, &rt6_stats_seq_fops);
#endif
+
+ mem_reserve_init(&ipv6_route_reserve, "IPv6 route cache",
+ &net_rx_reserve);
+ mem_reserve_kmem_cache_set(&ipv6_route_reserve,
+ ip6_dst_ops.kmem_cachep, ip6_rt_max_size);
+
#ifdef CONFIG_XFRM
xfrm6_init();
#endif
Index: linux-2.6/include/linux/sysctl.h
===================================================================
--- linux-2.6.orig/include/linux/sysctl.h
+++ linux-2.6/include/linux/sysctl.h
@@ -966,6 +966,17 @@ typedef int proc_handler (struct ctl_tab
extern int proc_dostring(struct ctl_table *, int, struct file *,
void __user *, size_t *, loff_t *);
+
+extern int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
+ int *valp,
+ int write, void *data);
+
+extern int do_proc_dointvec(ctl_table *table, int write, struct file *filp,
+ void __user *buffer, size_t *lenp, loff_t *ppos,
+ int (*conv)(int *negp, unsigned long *lvalp, int *valp,
+ int write, void *data),
+ void *data);
+
extern int proc_dointvec(struct ctl_table *, int, struct file *,
void __user *, size_t *, loff_t *);
extern int proc_dointvec_bset(struct ctl_table *, int, struct file *,
Index: linux-2.6/kernel/sysctl.c
===================================================================
--- linux-2.6.orig/kernel/sysctl.c
+++ linux-2.6/kernel/sysctl.c
@@ -1702,7 +1702,7 @@ int proc_dostring(struct ctl_table *tabl
}
-static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
+int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
int *valp,
int write, void *data)
{
@@ -1721,6 +1721,8 @@ static int do_proc_dointvec_conv(int *ne
return 0;
}
+EXPORT_SYMBOL(do_proc_dointvec_conv);
+
static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
int write, struct file *filp, void __user *buffer,
size_t *lenp, loff_t *ppos,
@@ -1832,7 +1834,7 @@ static int __do_proc_dointvec(void *tbl_
#undef TMPBUFLEN
}
-static int do_proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+int do_proc_dointvec(struct ctl_table *table, int write, struct file *filp,
void __user *buffer, size_t *lenp, loff_t *ppos,
int (*conv)(int *negp, unsigned long *lvalp, int *valp,
int write, void *data),
@@ -1842,6 +1844,8 @@ static int do_proc_dointvec(struct ctl_t
buffer, lenp, ppos, conv, data);
}
+EXPORT_SYMBOL(do_proc_dointvec);
+
/**
* proc_dointvec - read a vector of integers
* @table: the sysctl table
--
^ permalink raw reply
* [PATCH 21/33] netvm: prevent a TCP specific deadlock
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: netvm-tcp-deadlock.patch --]
[-- Type: text/plain, Size: 2428 bytes --]
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.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
include/net/sock.h | 7 ++++---
net/core/stream.c | 5 +++--
2 files changed, 7 insertions(+), 5 deletions(-)
Index: linux-2.6/include/net/sock.h
===================================================================
--- linux-2.6.orig/include/net/sock.h
+++ linux-2.6/include/net/sock.h
@@ -743,7 +743,8 @@ static inline struct inode *SOCK_INODE(s
}
extern void __sk_stream_mem_reclaim(struct sock *sk);
-extern int sk_stream_mem_schedule(struct sock *sk, int size, int kind);
+extern int sk_stream_mem_schedule(struct sock *sk, struct sk_buff *skb,
+ int size, int kind);
#define SK_STREAM_MEM_QUANTUM ((int)PAGE_SIZE)
@@ -761,13 +762,13 @@ static inline void sk_stream_mem_reclaim
static inline int sk_stream_rmem_schedule(struct sock *sk, struct sk_buff *skb)
{
return (int)skb->truesize <= sk->sk_forward_alloc ||
- sk_stream_mem_schedule(sk, skb->truesize, 1);
+ sk_stream_mem_schedule(sk, skb, skb->truesize, 1);
}
static inline int sk_stream_wmem_schedule(struct sock *sk, int size)
{
return size <= sk->sk_forward_alloc ||
- sk_stream_mem_schedule(sk, size, 0);
+ sk_stream_mem_schedule(sk, NULL, size, 0);
}
/* Used by processes to "lock" a socket state, so that
Index: linux-2.6/net/core/stream.c
===================================================================
--- linux-2.6.orig/net/core/stream.c
+++ linux-2.6/net/core/stream.c
@@ -207,7 +207,7 @@ void __sk_stream_mem_reclaim(struct sock
EXPORT_SYMBOL(__sk_stream_mem_reclaim);
-int sk_stream_mem_schedule(struct sock *sk, int size, int kind)
+int sk_stream_mem_schedule(struct sock *sk, struct sk_buff *skb, int size, int kind)
{
int amt = sk_stream_pages(size);
@@ -224,7 +224,8 @@ int sk_stream_mem_schedule(struct sock *
/* Over hard limit. */
if (atomic_read(sk->sk_prot->memory_allocated) > sk->sk_prot->sysctl_mem[2]) {
sk->sk_prot->enter_memory_pressure();
- goto suppress_allocation;
+ if (!skb || (skb && !skb_emergency(skb)))
+ goto suppress_allocation;
}
/* Under pressure. */
--
^ permalink raw reply
* [PATCH 27/33] nfs: remove mempools
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: nfs-no-mempool.patch --]
[-- Type: text/plain, Size: 4918 bytes --]
With the introduction of the shared dirty page accounting in .19, NFS should
not be able to surpise the VM with all dirty pages. Thus it should always be
able to free some memory. Hence no more need for mempools.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
fs/nfs/read.c | 15 +++------------
fs/nfs/write.c | 27 +++++----------------------
2 files changed, 8 insertions(+), 34 deletions(-)
Index: linux-2.6/fs/nfs/read.c
===================================================================
--- linux-2.6.orig/fs/nfs/read.c
+++ linux-2.6/fs/nfs/read.c
@@ -33,13 +33,10 @@ static const struct rpc_call_ops nfs_rea
static const struct rpc_call_ops nfs_read_full_ops;
static struct kmem_cache *nfs_rdata_cachep;
-static mempool_t *nfs_rdata_mempool;
-
-#define MIN_POOL_READ (32)
struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount)
{
- struct nfs_read_data *p = mempool_alloc(nfs_rdata_mempool, GFP_NOFS);
+ struct nfs_read_data *p = kmem_cache_alloc(nfs_rdata_cachep, GFP_NOFS);
if (p) {
memset(p, 0, sizeof(*p));
@@ -50,7 +47,7 @@ struct nfs_read_data *nfs_readdata_alloc
else {
p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS);
if (!p->pagevec) {
- mempool_free(p, nfs_rdata_mempool);
+ kmem_cache_free(nfs_rdata_cachep, p);
p = NULL;
}
}
@@ -63,7 +60,7 @@ static void nfs_readdata_rcu_free(struct
struct nfs_read_data *p = container_of(head, struct nfs_read_data, task.u.tk_rcu);
if (p && (p->pagevec != &p->page_array[0]))
kfree(p->pagevec);
- mempool_free(p, nfs_rdata_mempool);
+ kmem_cache_free(nfs_rdata_cachep, p);
}
static void nfs_readdata_free(struct nfs_read_data *rdata)
@@ -597,16 +594,10 @@ int __init nfs_init_readpagecache(void)
if (nfs_rdata_cachep == NULL)
return -ENOMEM;
- nfs_rdata_mempool = mempool_create_slab_pool(MIN_POOL_READ,
- nfs_rdata_cachep);
- if (nfs_rdata_mempool == NULL)
- return -ENOMEM;
-
return 0;
}
void nfs_destroy_readpagecache(void)
{
- mempool_destroy(nfs_rdata_mempool);
kmem_cache_destroy(nfs_rdata_cachep);
}
Index: linux-2.6/fs/nfs/write.c
===================================================================
--- linux-2.6.orig/fs/nfs/write.c
+++ linux-2.6/fs/nfs/write.c
@@ -28,9 +28,6 @@
#define NFSDBG_FACILITY NFSDBG_PAGECACHE
-#define MIN_POOL_WRITE (32)
-#define MIN_POOL_COMMIT (4)
-
/*
* Local function declarations
*/
@@ -44,12 +41,10 @@ static const struct rpc_call_ops nfs_wri
static const struct rpc_call_ops nfs_commit_ops;
static struct kmem_cache *nfs_wdata_cachep;
-static mempool_t *nfs_wdata_mempool;
-static mempool_t *nfs_commit_mempool;
struct nfs_write_data *nfs_commit_alloc(void)
{
- struct nfs_write_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOFS);
+ struct nfs_write_data *p = kmem_cache_alloc(nfs_wdata_cachep, GFP_NOFS);
if (p) {
memset(p, 0, sizeof(*p));
@@ -63,7 +58,7 @@ static void nfs_commit_rcu_free(struct r
struct nfs_write_data *p = container_of(head, struct nfs_write_data, task.u.tk_rcu);
if (p && (p->pagevec != &p->page_array[0]))
kfree(p->pagevec);
- mempool_free(p, nfs_commit_mempool);
+ kmem_cache_free(nfs_wdata_cachep, p);
}
void nfs_commit_free(struct nfs_write_data *wdata)
@@ -73,7 +68,7 @@ void nfs_commit_free(struct nfs_write_da
struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount)
{
- struct nfs_write_data *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS);
+ struct nfs_write_data *p = kmem_cache_alloc(nfs_wdata_cachep, GFP_NOFS);
if (p) {
memset(p, 0, sizeof(*p));
@@ -84,7 +79,7 @@ struct nfs_write_data *nfs_writedata_all
else {
p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS);
if (!p->pagevec) {
- mempool_free(p, nfs_wdata_mempool);
+ kmem_cache_free(nfs_wdata_cachep, p);
p = NULL;
}
}
@@ -97,7 +92,7 @@ static void nfs_writedata_rcu_free(struc
struct nfs_write_data *p = container_of(head, struct nfs_write_data, task.u.tk_rcu);
if (p && (p->pagevec != &p->page_array[0]))
kfree(p->pagevec);
- mempool_free(p, nfs_wdata_mempool);
+ kmem_cache_free(nfs_wdata_cachep, p);
}
static void nfs_writedata_free(struct nfs_write_data *wdata)
@@ -1474,16 +1469,6 @@ int __init nfs_init_writepagecache(void)
if (nfs_wdata_cachep == NULL)
return -ENOMEM;
- nfs_wdata_mempool = mempool_create_slab_pool(MIN_POOL_WRITE,
- nfs_wdata_cachep);
- if (nfs_wdata_mempool == NULL)
- return -ENOMEM;
-
- nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT,
- nfs_wdata_cachep);
- if (nfs_commit_mempool == NULL)
- return -ENOMEM;
-
/*
* NFS congestion size, scale with available memory.
*
@@ -1509,8 +1494,6 @@ int __init nfs_init_writepagecache(void)
void nfs_destroy_writepagecache(void)
{
- mempool_destroy(nfs_commit_mempool);
- mempool_destroy(nfs_wdata_mempool);
kmem_cache_destroy(nfs_wdata_cachep);
}
--
^ permalink raw reply
* [PATCH 29/33] nfs: disable data cache revalidation for swapfiles
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: nfs-swapper.patch --]
[-- Type: text/plain, Size: 5285 bytes --]
Do as Trond suggested:
http://lkml.org/lkml/2006/8/25/348
Disable NFS data cache revalidation on swap files since it doesn't really
make sense to have other clients change the file while you are using it.
Thereby we can stop setting PG_private on swap pages, since there ought to
be no further races with invalidate_inode_pages2() to deal with.
And since we cannot set PG_private we cannot use page->private (which is
already used by PG_swapcache pages anyway) to store the nfs_page. Thus
augment the new nfs_page_find_request logic.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
fs/nfs/inode.c | 6 ++++
fs/nfs/write.c | 73 ++++++++++++++++++++++++++++++++++++++++++++++-----------
2 files changed, 65 insertions(+), 14 deletions(-)
Index: linux-2.6/fs/nfs/inode.c
===================================================================
--- linux-2.6.orig/fs/nfs/inode.c
+++ linux-2.6/fs/nfs/inode.c
@@ -744,6 +744,12 @@ int nfs_revalidate_mapping_nolock(struct
struct nfs_inode *nfsi = NFS_I(inode);
int ret = 0;
+ /*
+ * swapfiles are not supposed to be shared.
+ */
+ if (IS_SWAPFILE(inode))
+ goto out;
+
if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
|| nfs_attribute_timeout(inode) || NFS_STALE(inode)) {
ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
Index: linux-2.6/fs/nfs/write.c
===================================================================
--- linux-2.6.orig/fs/nfs/write.c
+++ linux-2.6/fs/nfs/write.c
@@ -112,25 +112,62 @@ static void nfs_context_set_write_error(
set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
}
-static struct nfs_page *nfs_page_find_request_locked(struct page *page)
+static struct nfs_page *
+__nfs_page_find_request_locked(struct nfs_inode *nfsi, struct page *page, int get)
{
struct nfs_page *req = NULL;
- if (PagePrivate(page)) {
+ if (PagePrivate(page))
req = (struct nfs_page *)page_private(page);
- if (req != NULL)
- kref_get(&req->wb_kref);
- }
+ else if (unlikely(PageSwapCache(page)))
+ req = radix_tree_lookup(&nfsi->nfs_page_tree, page_file_index(page));
+
+ if (get && req)
+ kref_get(&req->wb_kref);
+
return req;
}
+static inline struct nfs_page *
+nfs_page_find_request_locked(struct nfs_inode *nfsi, struct page *page)
+{
+ return __nfs_page_find_request_locked(nfsi, page, 1);
+}
+
+static int __nfs_page_has_request(struct page *page)
+{
+ struct inode *inode = page_file_mapping(page)->host;
+ struct nfs_page *req = NULL;
+
+ spin_lock(&inode->i_lock);
+ req = __nfs_page_find_request_locked(NFS_I(inode), page, 0);
+ spin_unlock(&inode->i_lock);
+
+ /*
+ * hole here plugged by the caller holding onto PG_locked
+ */
+
+ return req != NULL;
+}
+
+static inline int nfs_page_has_request(struct page *page)
+{
+ if (PagePrivate(page))
+ return 1;
+
+ if (unlikely(PageSwapCache(page)))
+ return __nfs_page_has_request(page);
+
+ return 0;
+}
+
static struct nfs_page *nfs_page_find_request(struct page *page)
{
struct inode *inode = page_file_mapping(page)->host;
struct nfs_page *req = NULL;
spin_lock(&inode->i_lock);
- req = nfs_page_find_request_locked(page);
+ req = nfs_page_find_request_locked(NFS_I(inode), page);
spin_unlock(&inode->i_lock);
return req;
}
@@ -255,7 +292,7 @@ static int nfs_page_async_flush(struct n
spin_lock(&inode->i_lock);
for(;;) {
- req = nfs_page_find_request_locked(page);
+ req = nfs_page_find_request_locked(nfsi, page);
if (req == NULL) {
spin_unlock(&inode->i_lock);
return 0;
@@ -374,8 +411,14 @@ static int nfs_inode_add_request(struct
if (nfs_have_delegation(inode, FMODE_WRITE))
nfsi->change_attr++;
}
- SetPagePrivate(req->wb_page);
- set_page_private(req->wb_page, (unsigned long)req);
+ /*
+ * Swap-space should not get truncated. Hence no need to plug the race
+ * with invalidate/truncate.
+ */
+ if (likely(!PageSwapCache(req->wb_page))) {
+ SetPagePrivate(req->wb_page);
+ set_page_private(req->wb_page, (unsigned long)req);
+ }
nfsi->npages++;
kref_get(&req->wb_kref);
return 0;
@@ -392,8 +435,10 @@ static void nfs_inode_remove_request(str
BUG_ON (!NFS_WBACK_BUSY(req));
spin_lock(&inode->i_lock);
- set_page_private(req->wb_page, 0);
- ClearPagePrivate(req->wb_page);
+ if (likely(!PageSwapCache(req->wb_page))) {
+ set_page_private(req->wb_page, 0);
+ ClearPagePrivate(req->wb_page);
+ }
radix_tree_delete(&nfsi->nfs_page_tree, req->wb_index);
nfsi->npages--;
if (!nfsi->npages) {
@@ -592,7 +637,7 @@ static struct nfs_page * nfs_update_requ
* A request for the page we wish to update
*/
spin_lock(&inode->i_lock);
- req = nfs_page_find_request_locked(page);
+ req = nfs_page_find_request_locked(NFS_I(inode), page);
if (req) {
if (!nfs_lock_request_dontget(req)) {
int error;
@@ -1416,7 +1461,7 @@ int nfs_wb_page_cancel(struct inode *ino
if (ret < 0)
goto out;
}
- if (!PagePrivate(page))
+ if (!nfs_page_has_request(page))
return 0;
ret = nfs_sync_mapping_wait(page_file_mapping(page), &wbc, FLUSH_INVALIDATE);
out:
@@ -1443,7 +1488,7 @@ static int nfs_wb_page_priority(struct i
if (ret < 0)
goto out;
}
- if (!PagePrivate(page))
+ if (!nfs_page_has_request(page))
return 0;
ret = nfs_sync_mapping_wait(page_file_mapping(page), &wbc, how);
if (ret >= 0)
--
^ permalink raw reply
* [PATCH 31/33] nfs: enable swap on NFS
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: nfs-swapfile.patch --]
[-- Type: text/plain, Size: 9310 bytes --]
Provide an a_ops->swapfile() implementation for NFS. This will set the
NFS socket to SOCK_MEMALLOC and run socket reconnect under PF_MEMALLOC as well
as reset SOCK_MEMALLOC before engaging the protocol ->connect() method.
PF_MEMALLOC should allow the allocation of struct socket and related objects
and the early (re)setting of SOCK_MEMALLOC should allow us to receive the packets
required for the TCP connection buildup.
(swapping continues over a server reset during heavy network traffic)
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
fs/Kconfig | 18 ++++++++++++
fs/nfs/file.c | 10 ++++++
include/linux/sunrpc/xprt.h | 5 ++-
net/sunrpc/sched.c | 9 ++++--
net/sunrpc/xprtsock.c | 63 ++++++++++++++++++++++++++++++++++++++++++++
5 files changed, 102 insertions(+), 3 deletions(-)
Index: linux-2.6/fs/nfs/file.c
===================================================================
--- linux-2.6.orig/fs/nfs/file.c
+++ linux-2.6/fs/nfs/file.c
@@ -371,6 +371,13 @@ static int nfs_launder_page(struct page
return nfs_wb_page(page_file_mapping(page)->host, page);
}
+#ifdef CONFIG_NFS_SWAP
+static int nfs_swapfile(struct address_space *mapping, int enable)
+{
+ return xs_swapper(NFS_CLIENT(mapping->host)->cl_xprt, enable);
+}
+#endif
+
const struct address_space_operations nfs_file_aops = {
.readpage = nfs_readpage,
.readpages = nfs_readpages,
@@ -385,6 +392,9 @@ const struct address_space_operations nf
.direct_IO = nfs_direct_IO,
#endif
.launder_page = nfs_launder_page,
+#ifdef CONFIG_NFS_SWAP
+ .swapfile = nfs_swapfile,
+#endif
};
static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct page *page)
Index: linux-2.6/include/linux/sunrpc/xprt.h
===================================================================
--- linux-2.6.orig/include/linux/sunrpc/xprt.h
+++ linux-2.6/include/linux/sunrpc/xprt.h
@@ -143,7 +143,9 @@ struct rpc_xprt {
unsigned int max_reqs; /* total slots */
unsigned long state; /* transport state */
unsigned char shutdown : 1, /* being shut down */
- resvport : 1; /* use a reserved port */
+ resvport : 1, /* use a reserved port */
+ swapper : 1; /* we're swapping over this
+ transport */
unsigned int bind_index; /* bind function index */
/*
@@ -246,6 +248,7 @@ struct rpc_rqst * xprt_lookup_rqst(struc
void xprt_complete_rqst(struct rpc_task *task, int copied);
void xprt_release_rqst_cong(struct rpc_task *task);
void xprt_disconnect(struct rpc_xprt *xprt);
+int xs_swapper(struct rpc_xprt *xprt, int enable);
/*
* Reserved bit positions in xprt->state
Index: linux-2.6/net/sunrpc/sched.c
===================================================================
--- linux-2.6.orig/net/sunrpc/sched.c
+++ linux-2.6/net/sunrpc/sched.c
@@ -761,7 +761,10 @@ struct rpc_buffer {
void *rpc_malloc(struct rpc_task *task, size_t size)
{
struct rpc_buffer *buf;
- gfp_t gfp = RPC_IS_SWAPPER(task) ? GFP_ATOMIC : GFP_NOWAIT;
+ gfp_t gfp = GFP_NOWAIT;
+
+ if (RPC_IS_SWAPPER(task))
+ gfp |= __GFP_MEMALLOC;
size += sizeof(struct rpc_buffer);
if (size <= RPC_BUFFER_MAXSIZE)
@@ -817,6 +820,8 @@ void rpc_init_task(struct rpc_task *task
atomic_set(&task->tk_count, 1);
task->tk_client = clnt;
task->tk_flags = flags;
+ if (clnt->cl_xprt->swapper)
+ task->tk_flags |= RPC_TASK_SWAPPER;
task->tk_ops = tk_ops;
if (tk_ops->rpc_call_prepare != NULL)
task->tk_action = rpc_prepare_task;
@@ -853,7 +858,7 @@ void rpc_init_task(struct rpc_task *task
static struct rpc_task *
rpc_alloc_task(void)
{
- return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOFS);
+ return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOIO);
}
static void rpc_free_task(struct rcu_head *rcu)
Index: linux-2.6/net/sunrpc/xprtsock.c
===================================================================
--- linux-2.6.orig/net/sunrpc/xprtsock.c
+++ linux-2.6/net/sunrpc/xprtsock.c
@@ -1397,6 +1397,9 @@ static void xs_udp_finish_connecting(str
transport->sock = sock;
transport->inet = sk;
+ if (xprt->swapper)
+ sk_set_memalloc(sk);
+
write_unlock_bh(&sk->sk_callback_lock);
}
xs_udp_do_set_buffer_size(xprt);
@@ -1414,11 +1417,15 @@ static void xs_udp_connect_worker4(struc
container_of(work, struct sock_xprt, connect_worker.work);
struct rpc_xprt *xprt = &transport->xprt;
struct socket *sock = transport->sock;
+ unsigned long pflags = current->flags;
int err, status = -EIO;
if (xprt->shutdown || !xprt_bound(xprt))
goto out;
+ if (xprt->swapper)
+ current->flags |= PF_MEMALLOC;
+
/* Start by resetting any existing state */
xs_close(xprt);
@@ -1441,6 +1448,7 @@ static void xs_udp_connect_worker4(struc
out:
xprt_wake_pending_tasks(xprt, status);
xprt_clear_connecting(xprt);
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
}
/**
@@ -1455,11 +1463,15 @@ static void xs_udp_connect_worker6(struc
container_of(work, struct sock_xprt, connect_worker.work);
struct rpc_xprt *xprt = &transport->xprt;
struct socket *sock = transport->sock;
+ unsigned long pflags = current->flags;
int err, status = -EIO;
if (xprt->shutdown || !xprt_bound(xprt))
goto out;
+ if (xprt->swapper)
+ current->flags |= PF_MEMALLOC;
+
/* Start by resetting any existing state */
xs_close(xprt);
@@ -1482,6 +1494,7 @@ static void xs_udp_connect_worker6(struc
out:
xprt_wake_pending_tasks(xprt, status);
xprt_clear_connecting(xprt);
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
}
/*
@@ -1541,6 +1554,9 @@ static int xs_tcp_finish_connecting(stru
write_unlock_bh(&sk->sk_callback_lock);
}
+ if (xprt->swapper)
+ sk_set_memalloc(transport->inet);
+
/* Tell the socket layer to start connecting... */
xprt->stat.connect_count++;
xprt->stat.connect_start = jiffies;
@@ -1559,11 +1575,15 @@ static void xs_tcp_connect_worker4(struc
container_of(work, struct sock_xprt, connect_worker.work);
struct rpc_xprt *xprt = &transport->xprt;
struct socket *sock = transport->sock;
+ unsigned long pflags = current->flags;
int err, status = -EIO;
if (xprt->shutdown || !xprt_bound(xprt))
goto out;
+ if (xprt->swapper)
+ current->flags |= PF_MEMALLOC;
+
if (!sock) {
/* start from scratch */
if ((err = sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock)) < 0) {
@@ -1606,6 +1626,7 @@ out:
xprt_wake_pending_tasks(xprt, status);
out_clear:
xprt_clear_connecting(xprt);
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
}
/**
@@ -1620,11 +1641,15 @@ static void xs_tcp_connect_worker6(struc
container_of(work, struct sock_xprt, connect_worker.work);
struct rpc_xprt *xprt = &transport->xprt;
struct socket *sock = transport->sock;
+ unsigned long pflags = current->flags;
int err, status = -EIO;
if (xprt->shutdown || !xprt_bound(xprt))
goto out;
+ if (xprt->swapper)
+ current->flags |= PF_MEMALLOC;
+
if (!sock) {
/* start from scratch */
if ((err = sock_create_kern(PF_INET6, SOCK_STREAM, IPPROTO_TCP, &sock)) < 0) {
@@ -1666,6 +1691,7 @@ out:
xprt_wake_pending_tasks(xprt, status);
out_clear:
xprt_clear_connecting(xprt);
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
}
/**
@@ -1985,6 +2011,43 @@ int init_socket_xprt(void)
return 0;
}
+#ifdef CONFIG_SUNRPC_SWAP
+#define RPC_BUF_RESERVE_PAGES \
+ kestimate_single(sizeof(struct rpc_rqst), GFP_KERNEL, RPC_MAX_SLOT_TABLE)
+#define RPC_RESERVE_PAGES (RPC_BUF_RESERVE_PAGES + TX_RESERVE_PAGES)
+
+/**
+ * xs_swapper - Tag this transport as being used for swap.
+ * @xprt: transport to tag
+ * @enable: enable/disable
+ *
+ */
+int xs_swapper(struct rpc_xprt *xprt, int enable)
+{
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+ int err = 0;
+
+ if (enable) {
+ /*
+ * keep one extra sock reference so the reserve won't dip
+ * when the socket gets reconnected.
+ */
+ err = sk_adjust_memalloc(1, RPC_RESERVE_PAGES);
+ if (!err) {
+ sk_set_memalloc(transport->inet);
+ xprt->swapper = 1;
+ }
+ } else if (xprt->swapper) {
+ xprt->swapper = 0;
+ sk_clear_memalloc(transport->inet);
+ sk_adjust_memalloc(-1, -RPC_RESERVE_PAGES);
+ }
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(xs_swapper);
+#endif
+
/**
* cleanup_socket_xprt - remove xprtsock's sysctls, unregister
*
Index: linux-2.6/fs/Kconfig
===================================================================
--- linux-2.6.orig/fs/Kconfig
+++ linux-2.6/fs/Kconfig
@@ -1690,6 +1690,18 @@ config NFS_DIRECTIO
causes open() to return EINVAL if a file residing in NFS is
opened with the O_DIRECT flag.
+config NFS_SWAP
+ bool "Provide swap over NFS support"
+ default n
+ depends on NFS_FS
+ select SUNRPC_SWAP
+ help
+ This option enables swapon to work on files located on NFS mounts.
+
+ For more details, see Documentation/vm_deadlock.txt
+
+ If unsure, say N.
+
config NFSD
tristate "NFS server support"
depends on INET
@@ -1824,6 +1836,12 @@ config SUNRPC_BIND34
If unsure, say N to get traditional behavior (version 2 rpcbind
requests only).
+config SUNRPC_SWAP
+ def_bool n
+ depends on SUNRPC
+ select NETVM
+ select SWAP_FILE
+
config RPCSEC_GSS_KRB5
tristate "Secure RPC: Kerberos V mechanism (EXPERIMENTAL)"
depends on SUNRPC && EXPERIMENTAL
--
^ permalink raw reply
* [PATCH 33/33] nfs: do not warn on radix tree node allocation failures
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: nfs_radix_nowarn.patch --]
[-- Type: text/plain, Size: 2425 bytes --]
GFP_ATOMIC failures are rather common, no not warn about them.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
fs/nfs/inode.c | 2 +-
fs/nfs/write.c | 10 ++++++++++
2 files changed, 11 insertions(+), 1 deletion(-)
Index: linux-2.6/fs/nfs/inode.c
===================================================================
--- linux-2.6.orig/fs/nfs/inode.c
+++ linux-2.6/fs/nfs/inode.c
@@ -1172,7 +1172,7 @@ static void init_once(struct kmem_cache
INIT_LIST_HEAD(&nfsi->open_files);
INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
- INIT_RADIX_TREE(&nfsi->nfs_page_tree, GFP_ATOMIC);
+ INIT_RADIX_TREE(&nfsi->nfs_page_tree, GFP_ATOMIC|__GFP_NOWARN);
nfsi->ncommit = 0;
nfsi->npages = 0;
nfs4_init_once(nfsi);
Index: linux-2.6/fs/nfs/write.c
===================================================================
--- linux-2.6.orig/fs/nfs/write.c
+++ linux-2.6/fs/nfs/write.c
@@ -652,6 +652,7 @@ static struct nfs_page * nfs_update_requ
struct inode *inode = mapping->host;
struct nfs_page *req, *new = NULL;
pgoff_t rqend, end;
+ int error;
end = offset + bytes;
@@ -659,6 +660,10 @@ static struct nfs_page * nfs_update_requ
/* Loop over all inode entries and see if we find
* A request for the page we wish to update
*/
+ error = radix_tree_preload(GFP_NOIO);
+ if (error)
+ return ERR_PTR(error);
+
spin_lock(&inode->i_lock);
req = nfs_page_find_request_locked(NFS_I(inode), page);
if (req) {
@@ -666,6 +671,7 @@ static struct nfs_page * nfs_update_requ
int error;
spin_unlock(&inode->i_lock);
+ radix_tree_preload_end();
error = nfs_wait_on_request(req);
nfs_release_request(req);
if (error < 0) {
@@ -676,6 +682,7 @@ static struct nfs_page * nfs_update_requ
continue;
}
spin_unlock(&inode->i_lock);
+ radix_tree_preload_end();
if (new)
nfs_release_request(new);
break;
@@ -687,13 +694,16 @@ static struct nfs_page * nfs_update_requ
error = nfs_inode_add_request(inode, new);
if (error) {
spin_unlock(&inode->i_lock);
+ radix_tree_preload_end();
nfs_unlock_request(new);
return ERR_PTR(error);
}
spin_unlock(&inode->i_lock);
+ radix_tree_preload_end();
return new;
}
spin_unlock(&inode->i_lock);
+ radix_tree_preload_end();
new = nfs_create_request(ctx, inode, page, offset, bytes);
if (IS_ERR(new))
--
^ permalink raw reply
* [PATCH 32/33] nfs: fix various memory recursions possible with swap over NFS.
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: nfs-alloc-recursions.patch --]
[-- Type: text/plain, Size: 1861 bytes --]
GFP_NOFS is not enough, since swap traffic is IO, hence fall back to GFP_NOIO.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
fs/nfs/pagelist.c | 2 +-
fs/nfs/write.c | 6 +++---
2 files changed, 4 insertions(+), 4 deletions(-)
Index: linux-2.6/fs/nfs/write.c
===================================================================
--- linux-2.6.orig/fs/nfs/write.c
+++ linux-2.6/fs/nfs/write.c
@@ -44,7 +44,7 @@ static struct kmem_cache *nfs_wdata_cach
struct nfs_write_data *nfs_commit_alloc(void)
{
- struct nfs_write_data *p = kmem_cache_alloc(nfs_wdata_cachep, GFP_NOFS);
+ struct nfs_write_data *p = kmem_cache_alloc(nfs_wdata_cachep, GFP_NOIO);
if (p) {
memset(p, 0, sizeof(*p));
@@ -68,7 +68,7 @@ void nfs_commit_free(struct nfs_write_da
struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount)
{
- struct nfs_write_data *p = kmem_cache_alloc(nfs_wdata_cachep, GFP_NOFS);
+ struct nfs_write_data *p = kmem_cache_alloc(nfs_wdata_cachep, GFP_NOIO);
if (p) {
memset(p, 0, sizeof(*p));
@@ -77,7 +77,7 @@ struct nfs_write_data *nfs_writedata_all
if (pagecount <= ARRAY_SIZE(p->page_array))
p->pagevec = p->page_array;
else {
- p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS);
+ p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOIO);
if (!p->pagevec) {
kmem_cache_free(nfs_wdata_cachep, p);
p = NULL;
Index: linux-2.6/fs/nfs/pagelist.c
===================================================================
--- linux-2.6.orig/fs/nfs/pagelist.c
+++ linux-2.6/fs/nfs/pagelist.c
@@ -27,7 +27,7 @@ static inline struct nfs_page *
nfs_page_alloc(void)
{
struct nfs_page *p;
- p = kmem_cache_alloc(nfs_page_cachep, GFP_KERNEL);
+ p = kmem_cache_alloc(nfs_page_cachep, GFP_NOIO);
if (p) {
memset(p, 0, sizeof(*p));
INIT_LIST_HEAD(&p->wb_list);
--
^ permalink raw reply
* [PATCH 05/33] mm: kmem_estimate_pages()
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: mm-kmem_estimate_pages.patch --]
[-- Type: text/plain, Size: 3845 bytes --]
Provide a method to get the upper bound on the pages needed to allocate
a given number of objects from a given kmem_cache.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
include/linux/slab.h | 3 +
mm/slub.c | 82 +++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 85 insertions(+)
Index: linux-2.6/include/linux/slab.h
===================================================================
--- linux-2.6.orig/include/linux/slab.h
+++ linux-2.6/include/linux/slab.h
@@ -60,6 +60,7 @@ void kmem_cache_free(struct kmem_cache *
unsigned int kmem_cache_size(struct kmem_cache *);
const char *kmem_cache_name(struct kmem_cache *);
int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr);
+unsigned kmem_estimate_pages(struct kmem_cache *cachep, gfp_t flags, int objects);
/*
* Please use this macro to create slab caches. Simply specify the
@@ -94,6 +95,8 @@ int kmem_ptr_validate(struct kmem_cache
void * __must_check krealloc(const void *, size_t, gfp_t);
void kfree(const void *);
size_t ksize(const void *);
+unsigned kestimate_single(size_t, gfp_t, int);
+unsigned kestimate(gfp_t, size_t);
/*
* Allocator specific definitions. These are mainly used to establish optimized
Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c
+++ linux-2.6/mm/slub.c
@@ -2293,6 +2293,37 @@ const char *kmem_cache_name(struct kmem_
EXPORT_SYMBOL(kmem_cache_name);
/*
+ * return the max number of pages required to allocated count
+ * objects from the given cache
+ */
+unsigned kmem_estimate_pages(struct kmem_cache *s, gfp_t flags, int objects)
+{
+ unsigned long slabs;
+
+ if (WARN_ON(!s) || WARN_ON(!s->objects))
+ return 0;
+
+ slabs = DIV_ROUND_UP(objects, s->objects);
+
+ /*
+ * Account the possible additional overhead if the slab holds more that
+ * one object.
+ */
+ if (s->objects > 1) {
+ /*
+ * Account the possible additional overhead if per cpu slabs
+ * are currently empty and have to be allocated. This is very
+ * unlikely but a possible scenario immediately after
+ * kmem_cache_shrink.
+ */
+ slabs += num_online_cpus();
+ }
+
+ return slabs << s->order;
+}
+EXPORT_SYMBOL_GPL(kmem_estimate_pages);
+
+/*
* Attempt to free all slabs on a node. Return the number of slabs we
* were unable to free.
*/
@@ -2630,6 +2661,57 @@ void kfree(const void *x)
EXPORT_SYMBOL(kfree);
/*
+ * return the max number of pages required to allocate @count objects
+ * of @size bytes from kmalloc given @flags.
+ */
+unsigned kestimate_single(size_t size, gfp_t flags, int count)
+{
+ struct kmem_cache *s = get_slab(size, flags);
+ if (!s)
+ return 0;
+
+ return kmem_estimate_pages(s, flags, count);
+
+}
+EXPORT_SYMBOL_GPL(kestimate_single);
+
+/*
+ * return the max number of pages required to allocate @bytes from kmalloc
+ * in an unspecified number of allocation of heterogeneous size.
+ */
+unsigned kestimate(gfp_t flags, size_t bytes)
+{
+ int i;
+ unsigned long pages;
+
+ /*
+ * multiply by two, in order to account the worst case slack space
+ * due to the power-of-two allocation sizes.
+ */
+ pages = DIV_ROUND_UP(2 * bytes, PAGE_SIZE);
+
+ /*
+ * add the kmem_cache overhead of each possible kmalloc cache
+ */
+ for (i = 1; i < PAGE_SHIFT; i++) {
+ struct kmem_cache *s;
+
+#ifdef CONFIG_ZONE_DMA
+ if (unlikely(flags & SLUB_DMA))
+ s = dma_kmalloc_cache(i, flags);
+ else
+#endif
+ s = &kmalloc_caches[i];
+
+ if (s)
+ pages += kmem_estimate_pages(s, flags, 0);
+ }
+
+ return pages;
+}
+EXPORT_SYMBOL_GPL(kestimate);
+
+/*
* kmem_cache_shrink removes empty slabs from the partial lists and sorts
* the remaining slabs by the number of items in use. The slabs with the
* most items in use come first. New allocations will then fill those up
--
^ permalink raw reply
* [PATCH 24/33] mm: prepare swap entry methods for use in page methods
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: mm-swap_entry_methods.patch --]
[-- Type: text/plain, Size: 5182 bytes --]
Move around the swap entry methods in preparation for use from
page methods.
Also provide a function to obtain the swap_info_struct backing
a swap cache page.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
include/linux/mm.h | 8 ++++++++
include/linux/swap.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
include/linux/swapops.h | 44 --------------------------------------------
mm/swapfile.c | 1 +
4 files changed, 57 insertions(+), 44 deletions(-)
Index: linux-2.6/include/linux/mm.h
===================================================================
--- linux-2.6.orig/include/linux/mm.h
+++ linux-2.6/include/linux/mm.h
@@ -12,6 +12,7 @@
#include <linux/prio_tree.h>
#include <linux/debug_locks.h>
#include <linux/mm_types.h>
+#include <linux/swap.h>
struct mempolicy;
struct anon_vma;
@@ -573,6 +574,13 @@ static inline struct address_space *page
return mapping;
}
+static inline struct swap_info_struct *page_swap_info(struct page *page)
+{
+ swp_entry_t swap = { .val = page_private(page) };
+ BUG_ON(!PageSwapCache(page));
+ return get_swap_info_struct(swp_type(swap));
+}
+
static inline int PageAnon(struct page *page)
{
return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
Index: linux-2.6/include/linux/swap.h
===================================================================
--- linux-2.6.orig/include/linux/swap.h
+++ linux-2.6/include/linux/swap.h
@@ -80,6 +80,50 @@ typedef struct {
} swp_entry_t;
/*
+ * swapcache pages are stored in the swapper_space radix tree. We want to
+ * get good packing density in that tree, so the index should be dense in
+ * the low-order bits.
+ *
+ * We arrange the `type' and `offset' fields so that `type' is at the five
+ * high-order bits of the swp_entry_t and `offset' is right-aligned in the
+ * remaining bits.
+ *
+ * swp_entry_t's are *never* stored anywhere in their arch-dependent format.
+ */
+#define SWP_TYPE_SHIFT(e) (sizeof(e.val) * 8 - MAX_SWAPFILES_SHIFT)
+#define SWP_OFFSET_MASK(e) ((1UL << SWP_TYPE_SHIFT(e)) - 1)
+
+/*
+ * Store a type+offset into a swp_entry_t in an arch-independent format
+ */
+static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset)
+{
+ swp_entry_t ret;
+
+ ret.val = (type << SWP_TYPE_SHIFT(ret)) |
+ (offset & SWP_OFFSET_MASK(ret));
+ return ret;
+}
+
+/*
+ * Extract the `type' field from a swp_entry_t. The swp_entry_t is in
+ * arch-independent format
+ */
+static inline unsigned swp_type(swp_entry_t entry)
+{
+ return (entry.val >> SWP_TYPE_SHIFT(entry));
+}
+
+/*
+ * Extract the `offset' field from a swp_entry_t. The swp_entry_t is in
+ * arch-independent format
+ */
+static inline pgoff_t swp_offset(swp_entry_t entry)
+{
+ return entry.val & SWP_OFFSET_MASK(entry);
+}
+
+/*
* current->reclaim_state points to one of these when a task is running
* memory reclaim
*/
@@ -326,6 +370,10 @@ static inline int valid_swaphandles(swp_
return 0;
}
+static inline struct swap_info_struct *get_swap_info_struct(unsigned type)
+{
+ return NULL;
+}
#define can_share_swap_page(p) (page_mapcount(p) == 1)
static inline int move_to_swap_cache(struct page *page, swp_entry_t entry)
Index: linux-2.6/include/linux/swapops.h
===================================================================
--- linux-2.6.orig/include/linux/swapops.h
+++ linux-2.6/include/linux/swapops.h
@@ -1,48 +1,4 @@
/*
- * swapcache pages are stored in the swapper_space radix tree. We want to
- * get good packing density in that tree, so the index should be dense in
- * the low-order bits.
- *
- * We arrange the `type' and `offset' fields so that `type' is at the five
- * high-order bits of the swp_entry_t and `offset' is right-aligned in the
- * remaining bits.
- *
- * swp_entry_t's are *never* stored anywhere in their arch-dependent format.
- */
-#define SWP_TYPE_SHIFT(e) (sizeof(e.val) * 8 - MAX_SWAPFILES_SHIFT)
-#define SWP_OFFSET_MASK(e) ((1UL << SWP_TYPE_SHIFT(e)) - 1)
-
-/*
- * Store a type+offset into a swp_entry_t in an arch-independent format
- */
-static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset)
-{
- swp_entry_t ret;
-
- ret.val = (type << SWP_TYPE_SHIFT(ret)) |
- (offset & SWP_OFFSET_MASK(ret));
- return ret;
-}
-
-/*
- * Extract the `type' field from a swp_entry_t. The swp_entry_t is in
- * arch-independent format
- */
-static inline unsigned swp_type(swp_entry_t entry)
-{
- return (entry.val >> SWP_TYPE_SHIFT(entry));
-}
-
-/*
- * Extract the `offset' field from a swp_entry_t. The swp_entry_t is in
- * arch-independent format
- */
-static inline pgoff_t swp_offset(swp_entry_t entry)
-{
- return entry.val & SWP_OFFSET_MASK(entry);
-}
-
-/*
* Convert the arch-dependent pte representation of a swp_entry_t into an
* arch-independent swp_entry_t.
*/
Index: linux-2.6/mm/swapfile.c
===================================================================
--- linux-2.6.orig/mm/swapfile.c
+++ linux-2.6/mm/swapfile.c
@@ -1768,6 +1768,7 @@ get_swap_info_struct(unsigned type)
{
return &swap_info[type];
}
+EXPORT_SYMBOL_GPL(get_swap_info_struct);
/*
* swap_lock prevents swap_map being freed. Don't grab an extra
--
^ permalink raw reply
* [PATCH 16/33] netvm: network reserve infrastructure
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: netvm-reserve.patch --]
[-- Type: text/plain, Size: 7354 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
@@ -50,6 +50,7 @@
#include <linux/skbuff.h> /* struct sk_buff */
#include <linux/mm.h>
#include <linux/security.h>
+#include <linux/reserve.h>
#include <linux/filter.h>
@@ -397,6 +398,7 @@ 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)
@@ -419,9 +421,40 @@ 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;
@@ -919,6 +1025,7 @@ void sk_free(struct sock *sk)
struct sk_filter *filter;
struct module *owner = sk->sk_prot_creator->owner;
+ sk_clear_memalloc(sk);
if (sk->sk_destruct)
sk->sk_destruct(sk);
@@ -1049,6 +1156,12 @@ 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
@@ -237,6 +237,9 @@ endmenu
source "net/rfkill/Kconfig"
source "net/9p/Kconfig"
+config NETVM
+ def_bool n
+
endif # if NET
endmenu # Networking
--
^ permalink raw reply
* [PATCH 08/33] mm: emergency pool
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: mm-page_alloc-emerg.patch --]
[-- Type: text/plain, Size: 6606 bytes --]
Provide means to reserve a specific amount of pages.
The emergency pool is separated from the min watermark because ALLOC_HARDER
and ALLOC_HIGH modify the watermark in a relative way and thus do not ensure
a strict minimum.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
include/linux/mmzone.h | 3 +
mm/page_alloc.c | 82 +++++++++++++++++++++++++++++++++++++++++++------
mm/vmstat.c | 6 +--
3 files changed, 78 insertions(+), 13 deletions(-)
Index: linux-2.6/include/linux/mmzone.h
===================================================================
--- linux-2.6.orig/include/linux/mmzone.h
+++ linux-2.6/include/linux/mmzone.h
@@ -213,7 +213,7 @@ enum zone_type {
struct zone {
/* Fields commonly accessed by the page allocator */
- unsigned long pages_min, pages_low, pages_high;
+ unsigned long pages_emerg, pages_min, pages_low, pages_high;
/*
* We don't know if the memory that we're going to allocate will be freeable
* or/and it will be released eventually, so to avoid totally wasting several
@@ -682,6 +682,7 @@ int sysctl_min_unmapped_ratio_sysctl_han
struct file *, void __user *, size_t *, loff_t *);
int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
struct file *, void __user *, size_t *, loff_t *);
+int adjust_memalloc_reserve(int pages);
extern int numa_zonelist_order_handler(struct ctl_table *, int,
struct file *, void __user *, size_t *, loff_t *);
Index: linux-2.6/mm/page_alloc.c
===================================================================
--- linux-2.6.orig/mm/page_alloc.c
+++ linux-2.6/mm/page_alloc.c
@@ -118,6 +118,8 @@ static char * const zone_names[MAX_NR_ZO
static DEFINE_SPINLOCK(min_free_lock);
int min_free_kbytes = 1024;
+static DEFINE_MUTEX(var_free_mutex);
+int var_free_kbytes;
unsigned long __meminitdata nr_kernel_pages;
unsigned long __meminitdata nr_all_pages;
@@ -1252,7 +1254,7 @@ int zone_watermark_ok(struct zone *z, in
if (alloc_flags & ALLOC_HARDER)
min -= min / 4;
- if (free_pages <= min + z->lowmem_reserve[classzone_idx])
+ if (free_pages <= min + z->lowmem_reserve[classzone_idx] + z->pages_emerg)
return 0;
for (o = 0; o < order; o++) {
/* At the next order, this order's pages become unavailable */
@@ -1733,8 +1735,8 @@ nofail_alloc:
nopage:
if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) {
printk(KERN_WARNING "%s: page allocation failure."
- " order:%d, mode:0x%x\n",
- p->comm, order, gfp_mask);
+ " order:%d, mode:0x%x, alloc_flags:0x%x, pflags:0x%x\n",
+ p->comm, order, gfp_mask, alloc_flags, p->flags);
dump_stack();
show_mem();
}
@@ -1952,9 +1954,9 @@ void show_free_areas(void)
"\n",
zone->name,
K(zone_page_state(zone, NR_FREE_PAGES)),
- K(zone->pages_min),
- K(zone->pages_low),
- K(zone->pages_high),
+ K(zone->pages_emerg + zone->pages_min),
+ K(zone->pages_emerg + zone->pages_low),
+ K(zone->pages_emerg + zone->pages_high),
K(zone_page_state(zone, NR_ACTIVE)),
K(zone_page_state(zone, NR_INACTIVE)),
K(zone->present_pages),
@@ -4113,7 +4115,7 @@ static void calculate_totalreserve_pages
}
/* we treat pages_high as reserved pages. */
- max += zone->pages_high;
+ max += zone->pages_high + zone->pages_emerg;
if (max > zone->present_pages)
max = zone->present_pages;
@@ -4170,7 +4172,8 @@ static void setup_per_zone_lowmem_reserv
*/
static void __setup_per_zone_pages_min(void)
{
- unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
+ unsigned pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
+ unsigned pages_emerg = var_free_kbytes >> (PAGE_SHIFT - 10);
unsigned long lowmem_pages = 0;
struct zone *zone;
unsigned long flags;
@@ -4182,11 +4185,13 @@ static void __setup_per_zone_pages_min(v
}
for_each_zone(zone) {
- u64 tmp;
+ u64 tmp, tmp_emerg;
spin_lock_irqsave(&zone->lru_lock, flags);
tmp = (u64)pages_min * zone->present_pages;
do_div(tmp, lowmem_pages);
+ tmp_emerg = (u64)pages_emerg * zone->present_pages;
+ do_div(tmp_emerg, lowmem_pages);
if (is_highmem(zone)) {
/*
* __GFP_HIGH and PF_MEMALLOC allocations usually don't
@@ -4205,12 +4210,14 @@ static void __setup_per_zone_pages_min(v
if (min_pages > 128)
min_pages = 128;
zone->pages_min = min_pages;
+ zone->pages_emerg = 0;
} else {
/*
* If it's a lowmem zone, reserve a number of pages
* proportionate to the zone's size.
*/
zone->pages_min = tmp;
+ zone->pages_emerg = tmp_emerg;
}
zone->pages_low = zone->pages_min + (tmp >> 2);
@@ -4232,6 +4239,63 @@ void setup_per_zone_pages_min(void)
spin_unlock_irqrestore(&min_free_lock, flags);
}
+static void __adjust_memalloc_reserve(int pages)
+{
+ var_free_kbytes += pages << (PAGE_SHIFT - 10);
+ BUG_ON(var_free_kbytes < 0);
+ setup_per_zone_pages_min();
+}
+
+static int test_reserve_limits(void)
+{
+ struct zone *zone;
+ int node;
+
+ for_each_zone(zone)
+ wakeup_kswapd(zone, 0);
+
+ for_each_online_node(node) {
+ struct page *page = alloc_pages_node(node, GFP_KERNEL, 0);
+ if (!page)
+ return -ENOMEM;
+
+ __free_page(page);
+ }
+
+ return 0;
+}
+
+/**
+ * adjust_memalloc_reserve - adjust the memalloc reserve
+ * @pages: number of pages to add
+ *
+ * It adds a number of pages to the memalloc reserve; if
+ * the number was positive it kicks reclaim into action to
+ * satisfy the higher watermarks.
+ *
+ * returns -ENOMEM when it failed to satisfy the watermarks.
+ */
+int adjust_memalloc_reserve(int pages)
+{
+ int err = 0;
+
+ mutex_lock(&var_free_mutex);
+ __adjust_memalloc_reserve(pages);
+ if (pages > 0) {
+ err = test_reserve_limits();
+ if (err) {
+ __adjust_memalloc_reserve(-pages);
+ goto unlock;
+ }
+ }
+ printk(KERN_DEBUG "Emergency reserve: %d\n", var_free_kbytes);
+
+unlock:
+ mutex_unlock(&var_free_mutex);
+ return err;
+}
+EXPORT_SYMBOL_GPL(adjust_memalloc_reserve);
+
/*
* Initialise min_free_kbytes.
*
Index: linux-2.6/mm/vmstat.c
===================================================================
--- linux-2.6.orig/mm/vmstat.c
+++ linux-2.6/mm/vmstat.c
@@ -752,9 +752,9 @@ static void zoneinfo_show_print(struct s
"\n spanned %lu"
"\n present %lu",
zone_page_state(zone, NR_FREE_PAGES),
- zone->pages_min,
- zone->pages_low,
- zone->pages_high,
+ zone->pages_emerg + zone->pages_min,
+ zone->pages_emerg + zone->pages_low,
+ zone->pages_emerg + zone->pages_high,
zone->pages_scanned,
zone->nr_scan_active, zone->nr_scan_inactive,
zone->spanned_pages,
--
^ permalink raw reply
* [PATCH 26/33] mm: methods for teaching filesystems about PG_swapcache pages
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: mm-page_file_methods.patch --]
[-- Type: text/plain, Size: 2792 bytes --]
In order to teach filesystems to handle swap cache pages, two new page
functions are introduced:
pgoff_t page_file_index(struct page *);
struct address_space *page_file_mapping(struct page *);
page_file_index - gives the offset of this page in the file in PAGE_CACHE_SIZE
blocks. Like page->index is for mapped pages, this function also gives the
correct index for PG_swapcache pages.
page_file_mapping - gives the mapping backing the actual page; that is for
swap cache pages it will give swap_file->f_mapping.
page_offset() is modified to use page_file_index(), so that it will give the
expected result, even for PG_swapcache pages.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
include/linux/mm.h | 26 ++++++++++++++++++++++++++
include/linux/pagemap.h | 2 +-
2 files changed, 27 insertions(+), 1 deletion(-)
Index: linux-2.6/include/linux/mm.h
===================================================================
--- linux-2.6.orig/include/linux/mm.h
+++ linux-2.6/include/linux/mm.h
@@ -13,6 +13,7 @@
#include <linux/debug_locks.h>
#include <linux/mm_types.h>
#include <linux/swap.h>
+#include <linux/fs.h>
struct mempolicy;
struct anon_vma;
@@ -581,6 +582,16 @@ static inline struct swap_info_struct *p
return get_swap_info_struct(swp_type(swap));
}
+static inline
+struct address_space *page_file_mapping(struct page *page)
+{
+#ifdef CONFIG_SWAP_FILE
+ if (unlikely(PageSwapCache(page)))
+ return page_swap_info(page)->swap_file->f_mapping;
+#endif
+ return page->mapping;
+}
+
static inline int PageAnon(struct page *page)
{
return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
@@ -598,6 +609,21 @@ static inline pgoff_t page_index(struct
}
/*
+ * Return the file index of the page. Regular pagecache pages use ->index
+ * whereas swapcache pages use swp_offset(->private)
+ */
+static inline pgoff_t page_file_index(struct page *page)
+{
+#ifdef CONFIG_SWAP_FILE
+ if (unlikely(PageSwapCache(page))) {
+ swp_entry_t swap = { .val = page_private(page) };
+ return swp_offset(swap);
+ }
+#endif
+ return page->index;
+}
+
+/*
* The atomic page->_mapcount, like _count, starts from -1:
* so that transitions both from it and to it can be tracked,
* using atomic_inc_and_test and atomic_add_negative(-1).
Index: linux-2.6/include/linux/pagemap.h
===================================================================
--- linux-2.6.orig/include/linux/pagemap.h
+++ linux-2.6/include/linux/pagemap.h
@@ -145,7 +145,7 @@ extern void __remove_from_page_cache(str
*/
static inline loff_t page_offset(struct page *page)
{
- return ((loff_t)page->index) << PAGE_CACHE_SHIFT;
+ return ((loff_t)page_file_index(page)) << PAGE_CACHE_SHIFT;
}
static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
--
^ permalink raw reply
* [PATCH 03/33] mm: slub: add knowledge of reserve pages
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: reserve-slab.patch --]
[-- Type: text/plain, Size: 3787 bytes --]
Restrict objects from reserve slabs (ALLOC_NO_WATERMARKS) to allocation
contexts that are entitled to it.
Care is taken to only touch the SLUB slow path.
This is done to ensure reserve pages don't leak out and get consumed.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
include/linux/slub_def.h | 1 +
mm/slub.c | 31 +++++++++++++++++++++++--------
2 files changed, 24 insertions(+), 8 deletions(-)
Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c
+++ linux-2.6/mm/slub.c
@@ -20,11 +20,12 @@
#include <linux/mempolicy.h>
#include <linux/ctype.h>
#include <linux/kallsyms.h>
+#include "internal.h"
/*
* Lock order:
* 1. slab_lock(page)
- * 2. slab->list_lock
+ * 2. node->list_lock
*
* The slab_lock protects operations on the object of a particular
* slab and its metadata in the page struct. If the slab lock
@@ -1074,7 +1075,7 @@ static void setup_object(struct kmem_cac
s->ctor(s, object);
}
-static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
+static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node, int *reserve)
{
struct page *page;
struct kmem_cache_node *n;
@@ -1090,6 +1091,7 @@ static struct page *new_slab(struct kmem
if (!page)
goto out;
+ *reserve = page->reserve;
n = get_node(s, page_to_nid(page));
if (n)
atomic_long_inc(&n->nr_slabs);
@@ -1468,10 +1470,22 @@ static void *__slab_alloc(struct kmem_ca
{
void **object;
struct page *new;
+ int reserve = 0;
if (!c->page)
goto new_slab;
+ if (unlikely(c->reserve)) {
+ /*
+ * If the current slab is a reserve slab and the current
+ * allocation context does not allow access to the reserves
+ * we must force an allocation to test the current levels.
+ */
+ if (!(gfp_to_alloc_flags(gfpflags) & ALLOC_NO_WATERMARKS))
+ goto alloc_slab;
+ reserve = 1;
+ }
+
slab_lock(c->page);
if (unlikely(!node_match(c, node)))
goto another_slab;
@@ -1479,10 +1493,9 @@ load_freelist:
object = c->page->freelist;
if (unlikely(!object))
goto another_slab;
- if (unlikely(SlabDebug(c->page)))
+ if (unlikely(SlabDebug(c->page) || reserve))
goto debug;
- object = c->page->freelist;
c->freelist = object[c->offset];
c->page->inuse = s->objects;
c->page->freelist = NULL;
@@ -1500,16 +1513,18 @@ new_slab:
goto load_freelist;
}
+alloc_slab:
if (gfpflags & __GFP_WAIT)
local_irq_enable();
- new = new_slab(s, gfpflags, node);
+ new = new_slab(s, gfpflags, node, &reserve);
if (gfpflags & __GFP_WAIT)
local_irq_disable();
if (new) {
c = get_cpu_slab(s, smp_processor_id());
+ c->reserve = reserve;
if (c->page) {
/*
* Someone else populated the cpu_slab while we
@@ -1537,8 +1552,7 @@ new_slab:
}
return NULL;
debug:
- object = c->page->freelist;
- if (!alloc_debug_processing(s, c->page, object, addr))
+ if (SlabDebug(c->page) && !alloc_debug_processing(s, c->page, object, addr))
goto another_slab;
c->page->inuse++;
@@ -2010,10 +2024,11 @@ static struct kmem_cache_node *early_kme
{
struct page *page;
struct kmem_cache_node *n;
+ int reserve;
BUG_ON(kmalloc_caches->size < sizeof(struct kmem_cache_node));
- page = new_slab(kmalloc_caches, gfpflags, node);
+ page = new_slab(kmalloc_caches, gfpflags, node, &reserve);
BUG_ON(!page);
if (page_to_nid(page) != node) {
Index: linux-2.6/include/linux/slub_def.h
===================================================================
--- linux-2.6.orig/include/linux/slub_def.h
+++ linux-2.6/include/linux/slub_def.h
@@ -17,6 +17,7 @@ struct kmem_cache_cpu {
int node;
unsigned int offset;
unsigned int objsize;
+ int reserve;
};
struct kmem_cache_node {
--
^ permalink raw reply
* [PATCH 30/33] nfs: swap vs nfs_writepage
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: nfs-fix-writepage.patch --]
[-- Type: text/plain, Size: 1184 bytes --]
For now just use the ->writepage() path for swap traffic. Trond would like
to see ->swap_page() or some such additional a_op.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
fs/nfs/write.c | 23 +++++++++++++++++++++++
1 file changed, 23 insertions(+)
Index: linux-2.6/fs/nfs/write.c
===================================================================
--- linux-2.6.orig/fs/nfs/write.c
+++ linux-2.6/fs/nfs/write.c
@@ -336,6 +336,29 @@ static int nfs_do_writepage(struct page
nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1);
+ if (unlikely(IS_SWAPFILE(inode))) {
+ struct rpc_cred *cred;
+ struct nfs_open_context *ctx;
+ int status;
+
+ cred = rpcauth_lookupcred(NFS_CLIENT(inode)->cl_auth, 0);
+ if (IS_ERR(cred))
+ return PTR_ERR(cred);
+
+ ctx = nfs_find_open_context(inode, cred, FMODE_WRITE);
+ if (!ctx)
+ return -EBADF;
+
+ status = nfs_writepage_setup(ctx, page, 0, nfs_page_length(page));
+
+ put_nfs_open_context(ctx);
+
+ if (status < 0) {
+ nfs_set_pageerror(page);
+ return status;
+ }
+ }
+
nfs_pageio_cond_complete(pgio, page->index);
return nfs_page_async_flush(pgio, page);
}
--
^ permalink raw reply
* [PATCH 02/33] mm: tag reseve pages
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: page_alloc-reserve.patch --]
[-- Type: text/plain, Size: 1265 bytes --]
Tag pages allocated from the reserves with a non-zero page->reserve.
This allows us to distinguish and account reserve pages.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
include/linux/mm_types.h | 1 +
mm/page_alloc.c | 4 +++-
2 files changed, 4 insertions(+), 1 deletion(-)
Index: linux-2.6/include/linux/mm_types.h
===================================================================
--- linux-2.6.orig/include/linux/mm_types.h
+++ linux-2.6/include/linux/mm_types.h
@@ -70,6 +70,7 @@ struct page {
union {
pgoff_t index; /* Our offset within mapping. */
void *freelist; /* SLUB: freelist req. slab lock */
+ int reserve; /* page_alloc: page is a reserve page */
};
struct list_head lru; /* Pageout list, eg. active_list
* protected by zone->lru_lock !
Index: linux-2.6/mm/page_alloc.c
===================================================================
--- linux-2.6.orig/mm/page_alloc.c
+++ linux-2.6/mm/page_alloc.c
@@ -1448,8 +1448,10 @@ zonelist_scan:
}
page = buffered_rmqueue(zonelist, zone, order, gfp_mask);
- if (page)
+ if (page) {
+ page->reserve = !!(alloc_flags & ALLOC_NO_WATERMARKS);
break;
+ }
this_zone_full:
if (NUMA_BUILD)
zlc_mark_zone_full(zonelist, z);
--
^ permalink raw reply
* [PATCH 17/33] sysctl: propagate conv errors
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: sysctl_parse_error.patch --]
[-- Type: text/plain, Size: 1251 bytes --]
Currently conv routines will only generate -EINVAL, allow for other
errors to be propagetd.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
kernel/sysctl.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
Index: linux-2.6/kernel/sysctl.c
===================================================================
--- linux-2.6.orig/kernel/sysctl.c
+++ linux-2.6/kernel/sysctl.c
@@ -1732,6 +1732,7 @@ static int __do_proc_dointvec(void *tbl_
int *i, vleft, first=1, neg, val;
unsigned long lval;
size_t left, len;
+ int ret = 0;
char buf[TMPBUFLEN], *p;
char __user *s = buffer;
@@ -1787,14 +1788,16 @@ static int __do_proc_dointvec(void *tbl_
s += len;
left -= len;
- if (conv(&neg, &lval, i, 1, data))
+ ret = conv(&neg, &lval, i, 1, data);
+ if (ret)
break;
} else {
p = buf;
if (!first)
*p++ = '\t';
- if (conv(&neg, &lval, i, 0, data))
+ ret = conv(&neg, &lval, i, 0, data);
+ if (ret)
break;
sprintf(p, "%s%lu", neg ? "-" : "", lval);
@@ -1823,11 +1826,9 @@ static int __do_proc_dointvec(void *tbl_
left--;
}
}
- if (write && first)
- return -EINVAL;
*lenp -= left;
*ppos += *lenp;
- return 0;
+ return ret;
#undef TMPBUFLEN
}
--
^ permalink raw reply
* [PATCH 28/33] nfs: teach the NFS client how to treat PG_swapcache pages
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: nfs-swapcache.patch --]
[-- Type: text/plain, Size: 12547 bytes --]
Replace all relevant occurences of page->index and page->mapping in the NFS
client with the new page_file_index() and page_file_mapping() functions.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
fs/nfs/file.c | 8 ++++----
fs/nfs/internal.h | 7 ++++---
fs/nfs/pagelist.c | 6 +++---
fs/nfs/read.c | 6 +++---
fs/nfs/write.c | 49 +++++++++++++++++++++++++------------------------
5 files changed, 39 insertions(+), 37 deletions(-)
Index: linux-2.6/fs/nfs/file.c
===================================================================
--- linux-2.6.orig/fs/nfs/file.c
+++ linux-2.6/fs/nfs/file.c
@@ -357,7 +357,7 @@ static void nfs_invalidate_page(struct p
if (offset != 0)
return;
/* Cancel any unstarted writes on this page */
- nfs_wb_page_cancel(page->mapping->host, page);
+ nfs_wb_page_cancel(page_file_mapping(page)->host, page);
}
static int nfs_release_page(struct page *page, gfp_t gfp)
@@ -368,7 +368,7 @@ static int nfs_release_page(struct page
static int nfs_launder_page(struct page *page)
{
- return nfs_wb_page(page->mapping->host, page);
+ return nfs_wb_page(page_file_mapping(page)->host, page);
}
const struct address_space_operations nfs_file_aops = {
@@ -397,13 +397,13 @@ static int nfs_vm_page_mkwrite(struct vm
loff_t offset;
lock_page(page);
- mapping = page->mapping;
+ mapping = page_file_mapping(page);
if (mapping != vma->vm_file->f_path.dentry->d_inode->i_mapping) {
unlock_page(page);
return -EINVAL;
}
pagelen = nfs_page_length(page);
- offset = (loff_t)page->index << PAGE_CACHE_SHIFT;
+ offset = (loff_t)page_file_index(page) << PAGE_CACHE_SHIFT;
unlock_page(page);
/*
Index: linux-2.6/fs/nfs/pagelist.c
===================================================================
--- linux-2.6.orig/fs/nfs/pagelist.c
+++ linux-2.6/fs/nfs/pagelist.c
@@ -77,11 +77,11 @@ nfs_create_request(struct nfs_open_conte
* update_nfs_request below if the region is not locked. */
req->wb_page = page;
atomic_set(&req->wb_complete, 0);
- req->wb_index = page->index;
+ req->wb_index = page_file_index(page);
page_cache_get(page);
BUG_ON(PagePrivate(page));
BUG_ON(!PageLocked(page));
- BUG_ON(page->mapping->host != inode);
+ BUG_ON(page_file_mapping(page)->host != inode);
req->wb_offset = offset;
req->wb_pgbase = offset;
req->wb_bytes = count;
@@ -383,7 +383,7 @@ void nfs_pageio_cond_complete(struct nfs
* nfs_scan_list - Scan a list for matching requests
* @nfsi: NFS inode
* @dst: Destination list
- * @idx_start: lower bound of page->index to scan
+ * @idx_start: lower bound of page_file_index(page) to scan
* @npages: idx_start + npages sets the upper bound to scan.
* @tag: tag to scan for
*
Index: linux-2.6/fs/nfs/read.c
===================================================================
--- linux-2.6.orig/fs/nfs/read.c
+++ linux-2.6/fs/nfs/read.c
@@ -460,11 +460,11 @@ static const struct rpc_call_ops nfs_rea
int nfs_readpage(struct file *file, struct page *page)
{
struct nfs_open_context *ctx;
- struct inode *inode = page->mapping->host;
+ struct inode *inode = page_file_mapping(page)->host;
int error;
dprintk("NFS: nfs_readpage (%p %ld@%lu)\n",
- page, PAGE_CACHE_SIZE, page->index);
+ page, PAGE_CACHE_SIZE, page_file_index(page));
nfs_inc_stats(inode, NFSIOS_VFSREADPAGE);
nfs_add_stats(inode, NFSIOS_READPAGES, 1);
@@ -511,7 +511,7 @@ static int
readpage_async_filler(void *data, struct page *page)
{
struct nfs_readdesc *desc = (struct nfs_readdesc *)data;
- struct inode *inode = page->mapping->host;
+ struct inode *inode = page_file_mapping(page)->host;
struct nfs_page *new;
unsigned int len;
int error;
Index: linux-2.6/fs/nfs/write.c
===================================================================
--- linux-2.6.orig/fs/nfs/write.c
+++ linux-2.6/fs/nfs/write.c
@@ -126,7 +126,7 @@ static struct nfs_page *nfs_page_find_re
static struct nfs_page *nfs_page_find_request(struct page *page)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = page_file_mapping(page)->host;
struct nfs_page *req = NULL;
spin_lock(&inode->i_lock);
@@ -138,13 +138,13 @@ static struct nfs_page *nfs_page_find_re
/* Adjust the file length if we're writing beyond the end */
static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int count)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = page_file_mapping(page)->host;
loff_t end, i_size = i_size_read(inode);
pgoff_t end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
- if (i_size > 0 && page->index < end_index)
+ if (i_size > 0 && page_file_index(page) < end_index)
return;
- end = ((loff_t)page->index << PAGE_CACHE_SHIFT) + ((loff_t)offset+count);
+ end = page_offset(page) + ((loff_t)offset+count);
if (i_size >= end)
return;
nfs_inc_stats(inode, NFSIOS_EXTENDWRITE);
@@ -155,7 +155,7 @@ static void nfs_grow_file(struct page *p
static void nfs_set_pageerror(struct page *page)
{
SetPageError(page);
- nfs_zap_mapping(page->mapping->host, page->mapping);
+ nfs_zap_mapping(page_file_mapping(page)->host, page_file_mapping(page));
}
/* We can set the PG_uptodate flag if we see that a write request
@@ -187,7 +187,7 @@ static int nfs_writepage_setup(struct nf
ret = PTR_ERR(req);
if (ret != -EBUSY)
return ret;
- ret = nfs_wb_page(page->mapping->host, page);
+ ret = nfs_wb_page(page_file_mapping(page)->host, page);
if (ret != 0)
return ret;
}
@@ -221,7 +221,7 @@ static int nfs_set_page_writeback(struct
int ret = test_set_page_writeback(page);
if (!ret) {
- struct inode *inode = page->mapping->host;
+ struct inode *inode = page_file_mapping(page)->host;
struct nfs_server *nfss = NFS_SERVER(inode);
if (atomic_long_inc_return(&nfss->writeback) >
@@ -233,7 +233,7 @@ static int nfs_set_page_writeback(struct
static void nfs_end_page_writeback(struct page *page)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = page_file_mapping(page)->host;
struct nfs_server *nfss = NFS_SERVER(inode);
end_page_writeback(page);
@@ -248,7 +248,7 @@ static void nfs_end_page_writeback(struc
static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
struct page *page)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = page_file_mapping(page)->host;
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_page *req;
int ret;
@@ -294,7 +294,7 @@ static int nfs_page_async_flush(struct n
static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = page_file_mapping(page)->host;
nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1);
@@ -311,7 +311,7 @@ static int nfs_writepage_locked(struct p
struct nfs_pageio_descriptor pgio;
int err;
- nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc));
+ nfs_pageio_init_write(&pgio, page_file_mapping(page)->host, wb_priority(wbc));
err = nfs_do_writepage(page, wbc, &pgio);
nfs_pageio_complete(&pgio);
if (err < 0)
@@ -442,7 +442,8 @@ nfs_mark_request_commit(struct nfs_page
NFS_PAGE_TAG_COMMIT);
spin_unlock(&inode->i_lock);
inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
- inc_bdi_stat(req->wb_page->mapping->backing_dev_info, BDI_RECLAIMABLE);
+ inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
+ BDI_RECLAIMABLE);
__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
}
@@ -529,7 +530,7 @@ static void nfs_cancel_commit_list(struc
while(!list_empty(head)) {
req = nfs_list_entry(head->next);
dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
- dec_bdi_stat(req->wb_page->mapping->backing_dev_info,
+ dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
BDI_RECLAIMABLE);
nfs_list_remove_request(req);
clear_bit(PG_NEED_COMMIT, &(req)->wb_flags);
@@ -543,7 +544,7 @@ static void nfs_cancel_commit_list(struc
* nfs_scan_commit - Scan an inode for commit requests
* @inode: NFS inode to scan
* @dst: destination list
- * @idx_start: lower bound of page->index to scan.
+ * @idx_start: lower bound of page_file_index(page) to scan.
* @npages: idx_start + npages sets the upper bound to scan.
*
* Moves requests from the inode's 'commit' request list.
@@ -579,7 +580,7 @@ static inline int nfs_scan_commit(struct
static struct nfs_page * nfs_update_request(struct nfs_open_context* ctx,
struct page *page, unsigned int offset, unsigned int bytes)
{
- struct address_space *mapping = page->mapping;
+ struct address_space *mapping = page_file_mapping(page);
struct inode *inode = mapping->host;
struct nfs_page *req, *new = NULL;
pgoff_t rqend, end;
@@ -681,7 +682,7 @@ int nfs_flush_incompatible(struct file *
nfs_release_request(req);
if (!do_flush)
return 0;
- status = nfs_wb_page(page->mapping->host, page);
+ status = nfs_wb_page(page_file_mapping(page)->host, page);
} while (status == 0);
return status;
}
@@ -696,7 +697,7 @@ int nfs_updatepage(struct file *file, st
unsigned int offset, unsigned int count)
{
struct nfs_open_context *ctx = nfs_file_open_context(file);
- struct inode *inode = page->mapping->host;
+ struct inode *inode = page_file_mapping(page)->host;
int status = 0;
nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE);
@@ -952,7 +953,7 @@ static void nfs_writeback_done_partial(s
}
if (nfs_write_need_commit(data)) {
- struct inode *inode = page->mapping->host;
+ struct inode *inode = page_file_mapping(page)->host;
spin_lock(&inode->i_lock);
if (test_bit(PG_NEED_RESCHED, &req->wb_flags)) {
@@ -1191,7 +1192,7 @@ nfs_commit_list(struct inode *inode, str
nfs_list_remove_request(req);
nfs_mark_request_commit(req);
dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
- dec_bdi_stat(req->wb_page->mapping->backing_dev_info,
+ dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
BDI_RECLAIMABLE);
nfs_clear_page_tag_locked(req);
}
@@ -1218,7 +1219,7 @@ static void nfs_commit_done(struct rpc_t
nfs_list_remove_request(req);
clear_bit(PG_NEED_COMMIT, &(req)->wb_flags);
dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
- dec_bdi_stat(req->wb_page->mapping->backing_dev_info,
+ dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
BDI_RECLAIMABLE);
dprintk("NFS: commit (%s/%Ld %d@%Ld)",
@@ -1384,7 +1385,7 @@ int nfs_wb_page_cancel(struct inode *ino
loff_t range_start = page_offset(page);
loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
struct writeback_control wbc = {
- .bdi = page->mapping->backing_dev_info,
+ .bdi = page_file_mapping(page)->backing_dev_info,
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = range_start,
@@ -1417,7 +1418,7 @@ int nfs_wb_page_cancel(struct inode *ino
}
if (!PagePrivate(page))
return 0;
- ret = nfs_sync_mapping_wait(page->mapping, &wbc, FLUSH_INVALIDATE);
+ ret = nfs_sync_mapping_wait(page_file_mapping(page), &wbc, FLUSH_INVALIDATE);
out:
return ret;
}
@@ -1428,7 +1429,7 @@ static int nfs_wb_page_priority(struct i
loff_t range_start = page_offset(page);
loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
struct writeback_control wbc = {
- .bdi = page->mapping->backing_dev_info,
+ .bdi = page_file_mapping(page)->backing_dev_info,
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = range_start,
@@ -1444,7 +1445,7 @@ static int nfs_wb_page_priority(struct i
}
if (!PagePrivate(page))
return 0;
- ret = nfs_sync_mapping_wait(page->mapping, &wbc, how);
+ ret = nfs_sync_mapping_wait(page_file_mapping(page), &wbc, how);
if (ret >= 0)
return 0;
out:
Index: linux-2.6/fs/nfs/internal.h
===================================================================
--- linux-2.6.orig/fs/nfs/internal.h
+++ linux-2.6/fs/nfs/internal.h
@@ -248,13 +248,14 @@ void nfs_super_set_maxbytes(struct super
static inline
unsigned int nfs_page_length(struct page *page)
{
- loff_t i_size = i_size_read(page->mapping->host);
+ loff_t i_size = i_size_read(page_file_mapping(page)->host);
if (i_size > 0) {
+ pgoff_t page_index = page_file_index(page);
pgoff_t end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
- if (page->index < end_index)
+ if (page_index < end_index)
return PAGE_CACHE_SIZE;
- if (page->index == end_index)
+ if (page_index == end_index)
return ((i_size - 1) & ~PAGE_CACHE_MASK) + 1;
}
return 0;
--
^ permalink raw reply
* [PATCH 22/33] netfilter: NF_QUEUE vs emergency skbs
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: emergency-nf_queue.patch --]
[-- Type: text/plain, Size: 863 bytes --]
Avoid memory getting stuck waiting for userspace, drop all emergency packets.
This of course requires the regular storage route to not include an NF_QUEUE
target ;-)
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
net/netfilter/core.c | 3 +++
1 file changed, 3 insertions(+)
Index: linux-2.6/net/netfilter/core.c
===================================================================
--- linux-2.6.orig/net/netfilter/core.c
+++ linux-2.6/net/netfilter/core.c
@@ -181,9 +181,12 @@ next_hook:
ret = 1;
goto unlock;
} else if (verdict == NF_DROP) {
+drop:
kfree_skb(*pskb);
ret = -EPERM;
} else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) {
+ if (skb_emergency(*pskb))
+ goto drop;
NFDEBUG("nf_hook: Verdict = QUEUE.\n");
if (!nf_queue(*pskb, elem, pf, hook, indev, outdev, okfn,
verdict >> NF_VERDICT_BITS))
--
^ permalink raw reply
* [PATCH 19/33] netvm: hook skb allocation to reserves
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: netvm-skbuff-reserve.patch --]
[-- Type: text/plain, Size: 14822 bytes --]
Change the skb allocation api to indicate RX usage and use this to fall back to
the reserve when needed. SKBs allocated from the reserve are tagged in
skb->emergency.
Teach all other skb ops about emergency skbs and the reserve accounting.
Use the (new) packet split API to allocate and track fragment pages from the
emergency reserve. Do this using an atomic counter in page->index. This is
needed because the fragments have a different sharing semantic than that
indicated by skb_shinfo()->dataref.
Note that the decision to distinguish between regular and emergency SKBs allows
the accounting overhead to be limited to the later kind.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
include/linux/mm_types.h | 1
include/linux/skbuff.h | 25 +++++-
net/core/skbuff.c | 173 +++++++++++++++++++++++++++++++++++++++++------
3 files changed, 173 insertions(+), 26 deletions(-)
Index: linux-2.6/include/linux/skbuff.h
===================================================================
--- linux-2.6.orig/include/linux/skbuff.h
+++ linux-2.6/include/linux/skbuff.h
@@ -289,7 +289,8 @@ struct sk_buff {
__u8 pkt_type:3,
fclone:2,
ipvs_property:1,
- nf_trace:1;
+ nf_trace:1,
+ emergency:1;
__be16 protocol;
void (*destructor)(struct sk_buff *skb);
@@ -341,10 +342,22 @@ struct sk_buff {
#include <asm/system.h>
+#define SKB_ALLOC_FCLONE 0x01
+#define SKB_ALLOC_RX 0x02
+
+static inline bool skb_emergency(const struct sk_buff *skb)
+{
+#ifdef CONFIG_NETVM
+ return unlikely(skb->emergency);
+#else
+ return false;
+#endif
+}
+
extern void kfree_skb(struct sk_buff *skb);
extern void __kfree_skb(struct sk_buff *skb);
extern struct sk_buff *__alloc_skb(unsigned int size,
- gfp_t priority, int fclone, int node);
+ gfp_t priority, int flags, int node);
static inline struct sk_buff *alloc_skb(unsigned int size,
gfp_t priority)
{
@@ -354,7 +367,7 @@ static inline struct sk_buff *alloc_skb(
static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
gfp_t priority)
{
- return __alloc_skb(size, priority, 1, -1);
+ return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, -1);
}
extern void kfree_skbmem(struct sk_buff *skb);
@@ -1297,7 +1310,8 @@ static inline void __skb_queue_purge(str
static inline struct sk_buff *__dev_alloc_skb(unsigned int length,
gfp_t gfp_mask)
{
- struct sk_buff *skb = alloc_skb(length + NET_SKB_PAD, gfp_mask);
+ struct sk_buff *skb =
+ __alloc_skb(length + NET_SKB_PAD, gfp_mask, SKB_ALLOC_RX, -1);
if (likely(skb))
skb_reserve(skb, NET_SKB_PAD);
return skb;
@@ -1343,6 +1357,7 @@ static inline struct sk_buff *netdev_all
}
extern struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask);
+extern void __netdev_free_page(struct net_device *dev, struct page *page);
/**
* netdev_alloc_page - allocate a page for ps-rx on a specific device
@@ -1359,7 +1374,7 @@ static inline struct page *netdev_alloc_
static inline void netdev_free_page(struct net_device *dev, struct page *page)
{
- __free_page(page);
+ __netdev_free_page(dev, page);
}
/**
Index: linux-2.6/net/core/skbuff.c
===================================================================
--- linux-2.6.orig/net/core/skbuff.c
+++ linux-2.6/net/core/skbuff.c
@@ -179,21 +179,28 @@ EXPORT_SYMBOL(skb_truesize_bug);
* %GFP_ATOMIC.
*/
struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
- int fclone, int node)
+ int flags, int node)
{
struct kmem_cache *cache;
struct skb_shared_info *shinfo;
struct sk_buff *skb;
u8 *data;
+ int emergency = 0, memalloc = sk_memalloc_socks();
- cache = fclone ? skbuff_fclone_cache : skbuff_head_cache;
+ size = SKB_DATA_ALIGN(size);
+ cache = (flags & SKB_ALLOC_FCLONE)
+ ? skbuff_fclone_cache : skbuff_head_cache;
+#ifdef CONFIG_NETVM
+ if (memalloc && (flags & SKB_ALLOC_RX))
+ gfp_mask |= __GFP_NOMEMALLOC|__GFP_NOWARN;
+retry_alloc:
+#endif
/* Get the HEAD */
skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node);
if (!skb)
- goto out;
+ goto noskb;
- size = SKB_DATA_ALIGN(size);
data = kmalloc_node_track_caller(size + sizeof(struct skb_shared_info),
gfp_mask, node);
if (!data)
@@ -203,6 +210,7 @@ struct sk_buff *__alloc_skb(unsigned int
* See comment in sk_buff definition, just before the 'tail' member
*/
memset(skb, 0, offsetof(struct sk_buff, tail));
+ skb->emergency = emergency;
skb->truesize = size + sizeof(struct sk_buff);
atomic_set(&skb->users, 1);
skb->head = data;
@@ -219,7 +227,7 @@ struct sk_buff *__alloc_skb(unsigned int
shinfo->ip6_frag_id = 0;
shinfo->frag_list = NULL;
- if (fclone) {
+ if (flags & SKB_ALLOC_FCLONE) {
struct sk_buff *child = skb + 1;
atomic_t *fclone_ref = (atomic_t *) (child + 1);
@@ -227,12 +235,31 @@ struct sk_buff *__alloc_skb(unsigned int
atomic_set(fclone_ref, 1);
child->fclone = SKB_FCLONE_UNAVAILABLE;
+ child->emergency = skb->emergency;
}
out:
return skb;
+
nodata:
kmem_cache_free(cache, skb);
skb = NULL;
+noskb:
+#ifdef CONFIG_NETVM
+ /* Attempt emergency allocation when RX skb. */
+ if (likely(!(flags & SKB_ALLOC_RX) || !memalloc))
+ goto out;
+
+ if (!emergency) {
+ if (rx_emergency_get(size)) {
+ gfp_mask &= ~(__GFP_NOMEMALLOC|__GFP_NOWARN);
+ gfp_mask |= __GFP_MEMALLOC;
+ emergency = 1;
+ goto retry_alloc;
+ }
+ } else
+ rx_emergency_put(size);
+#endif
+
goto out;
}
@@ -255,7 +282,7 @@ struct sk_buff *__netdev_alloc_skb(struc
int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1;
struct sk_buff *skb;
- skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, node);
+ skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, SKB_ALLOC_RX, node);
if (likely(skb)) {
skb_reserve(skb, NET_SKB_PAD);
skb->dev = dev;
@@ -268,10 +295,34 @@ struct page *__netdev_alloc_page(struct
int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1;
struct page *page;
+#ifdef CONFIG_NETVM
+ gfp_mask |= __GFP_NOMEMALLOC | __GFP_NOWARN;
+#endif
+
page = alloc_pages_node(node, gfp_mask, 0);
+
+#ifdef CONFIG_NETVM
+ if (!page && rx_emergency_get(PAGE_SIZE)) {
+ gfp_mask &= ~(__GFP_NOMEMALLOC | __GFP_NOWARN);
+ gfp_mask |= __GFP_MEMALLOC;
+ page = alloc_pages_node(node, gfp_mask, 0);
+ if (!page)
+ rx_emergency_put(PAGE_SIZE);
+ }
+#endif
+
return page;
}
+void __netdev_free_page(struct net_device *dev, struct page *page)
+{
+#ifdef CONFIG_NETVM
+ if (unlikely(page->reserve))
+ rx_emergency_put(PAGE_SIZE);
+#endif
+ __free_page(page);
+}
+
void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
int size)
{
@@ -279,6 +330,34 @@ void skb_add_rx_frag(struct sk_buff *skb
skb->len += size;
skb->data_len += size;
skb->truesize += size;
+
+#ifdef CONFIG_NETVM
+ /*
+ * Fix-up the emergency accounting; make sure all pages match
+ * skb->emergency.
+ *
+ * This relies on page->reserve to be preserved between
+ * the call to __netdev_alloc_page() and this call.
+ */
+ if (skb_emergency(skb)) {
+ /*
+ * If the page was not an emergency alloc (ALLOC_NO_WATERMARK)
+ * we can use overcommit accounting, since we already have the
+ * memory.
+ */
+ if (!page->reserve)
+ rx_emergency_get_overcommit(PAGE_SIZE);
+ atomic_set(&page->frag_count, 1);
+ } else if (unlikely(page->reserve)) {
+ /*
+ * Rare case; the skb wasn't allocated under pressure but
+ * the page was. We need to return the page. This can offset
+ * the accounting a little, but its a constant shift, it does
+ * not accumulate.
+ */
+ rx_emergency_put(PAGE_SIZE);
+ }
+#endif
}
static void skb_drop_list(struct sk_buff **listp)
@@ -307,21 +386,45 @@ static void skb_clone_fraglist(struct sk
skb_get(list);
}
+static inline void skb_get_page(struct sk_buff *skb, struct page *page)
+{
+ get_page(page);
+ if (skb_emergency(skb))
+ atomic_inc(&page->frag_count);
+}
+
+static inline void skb_put_page(struct sk_buff *skb, struct page *page)
+{
+ if (skb_emergency(skb) && atomic_dec_and_test(&page->frag_count))
+ rx_emergency_put(PAGE_SIZE);
+ put_page(page);
+}
+
static void skb_release_data(struct sk_buff *skb)
{
if (!skb->cloned ||
!atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1,
&skb_shinfo(skb)->dataref)) {
+ int size;
+
+#ifdef NET_SKBUFF_DATA_USES_OFFSET
+ size = skb->end;
+#else
+ size = skb->end - skb->head;
+#endif
+
if (skb_shinfo(skb)->nr_frags) {
int i;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
- put_page(skb_shinfo(skb)->frags[i].page);
+ skb_put_page(skb, skb_shinfo(skb)->frags[i].page);
}
if (skb_shinfo(skb)->frag_list)
skb_drop_fraglist(skb);
kfree(skb->head);
+ if (skb_emergency(skb))
+ rx_emergency_put(size);
}
}
@@ -440,6 +543,9 @@ struct sk_buff *skb_clone(struct sk_buff
n->fclone = SKB_FCLONE_CLONE;
atomic_inc(fclone_ref);
} else {
+ if (skb_emergency(skb))
+ gfp_mask |= __GFP_MEMALLOC;
+
n = kmem_cache_alloc(skbuff_head_cache, gfp_mask);
if (!n)
return NULL;
@@ -477,6 +583,7 @@ struct sk_buff *skb_clone(struct sk_buff
#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
C(ipvs_property);
#endif
+ C(emergency);
C(protocol);
n->destructor = NULL;
C(mark);
@@ -565,6 +672,14 @@ static void copy_skb_header(struct sk_bu
skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
}
+static inline int skb_alloc_rx_flag(const struct sk_buff *skb)
+{
+ if (skb_emergency(skb))
+ return SKB_ALLOC_RX;
+
+ return 0;
+}
+
/**
* skb_copy - create private copy of an sk_buff
* @skb: buffer to copy
@@ -585,15 +700,17 @@ static void copy_skb_header(struct sk_bu
struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
{
int headerlen = skb->data - skb->head;
+ int size;
/*
* Allocate the copy buffer
*/
struct sk_buff *n;
#ifdef NET_SKBUFF_DATA_USES_OFFSET
- n = alloc_skb(skb->end + skb->data_len, gfp_mask);
+ size = skb->end + skb->data_len;
#else
- n = alloc_skb(skb->end - skb->head + skb->data_len, gfp_mask);
+ size = skb->end - skb->head + skb->data_len;
#endif
+ n = __alloc_skb(size, gfp_mask, skb_alloc_rx_flag(skb), -1);
if (!n)
return NULL;
@@ -628,12 +745,14 @@ struct sk_buff *pskb_copy(struct sk_buff
/*
* Allocate the copy buffer
*/
+ int size;
struct sk_buff *n;
#ifdef NET_SKBUFF_DATA_USES_OFFSET
- n = alloc_skb(skb->end, gfp_mask);
+ size = skb->end;
#else
- n = alloc_skb(skb->end - skb->head, gfp_mask);
+ size = skb->end - skb->head;
#endif
+ n = __alloc_skb(size, gfp_mask, skb_alloc_rx_flag(skb), -1);
if (!n)
goto out;
@@ -652,8 +771,9 @@ struct sk_buff *pskb_copy(struct sk_buff
int i;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
- skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i];
- get_page(skb_shinfo(n)->frags[i].page);
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+ skb_shinfo(n)->frags[i] = *frag;
+ skb_get_page(n, frag->page);
}
skb_shinfo(n)->nr_frags = i;
}
@@ -701,6 +821,14 @@ int pskb_expand_head(struct sk_buff *skb
size = SKB_DATA_ALIGN(size);
+ if (skb_emergency(skb)) {
+ if (rx_emergency_get(size))
+ gfp_mask |= __GFP_MEMALLOC;
+ else
+ goto nodata;
+ } else
+ gfp_mask |= __GFP_NOMEMALLOC;
+
data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
if (!data)
goto nodata;
@@ -716,7 +844,7 @@ int pskb_expand_head(struct sk_buff *skb
sizeof(struct skb_shared_info));
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
- get_page(skb_shinfo(skb)->frags[i].page);
+ skb_get_page(skb, skb_shinfo(skb)->frags[i].page);
if (skb_shinfo(skb)->frag_list)
skb_clone_fraglist(skb);
@@ -795,8 +923,8 @@ struct sk_buff *skb_copy_expand(const st
/*
* Allocate the copy buffer
*/
- struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom,
- gfp_mask);
+ struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom,
+ gfp_mask, skb_alloc_rx_flag(skb), -1);
int oldheadroom = skb_headroom(skb);
int head_copy_len, head_copy_off;
int off;
@@ -913,7 +1041,7 @@ drop_pages:
skb_shinfo(skb)->nr_frags = i;
for (; i < nfrags; i++)
- put_page(skb_shinfo(skb)->frags[i].page);
+ skb_put_page(skb, skb_shinfo(skb)->frags[i].page);
if (skb_shinfo(skb)->frag_list)
skb_drop_fraglist(skb);
@@ -1082,7 +1210,7 @@ pull_pages:
k = 0;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
if (skb_shinfo(skb)->frags[i].size <= eat) {
- put_page(skb_shinfo(skb)->frags[i].page);
+ skb_put_page(skb, skb_shinfo(skb)->frags[i].page);
eat -= skb_shinfo(skb)->frags[i].size;
} else {
skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i];
@@ -1854,6 +1982,7 @@ static inline void skb_split_no_header(s
skb_shinfo(skb1)->frags[k] = skb_shinfo(skb)->frags[i];
if (pos < len) {
+ struct page *page = skb_shinfo(skb)->frags[i].page;
/* Split frag.
* We have two variants in this case:
* 1. Move all the frag to the second
@@ -1862,7 +1991,7 @@ static inline void skb_split_no_header(s
* where splitting is expensive.
* 2. Split is accurately. We make this.
*/
- get_page(skb_shinfo(skb)->frags[i].page);
+ skb_get_page(skb1, page);
skb_shinfo(skb1)->frags[0].page_offset += len - pos;
skb_shinfo(skb1)->frags[0].size -= len - pos;
skb_shinfo(skb)->frags[i].size = len - pos;
@@ -2193,7 +2322,8 @@ struct sk_buff *skb_segment(struct sk_bu
if (hsize > len || !sg)
hsize = len;
- nskb = alloc_skb(hsize + doffset + headroom, GFP_ATOMIC);
+ nskb = __alloc_skb(hsize + doffset + headroom, GFP_ATOMIC,
+ skb_alloc_rx_flag(skb), -1);
if (unlikely(!nskb))
goto err;
@@ -2238,7 +2368,7 @@ struct sk_buff *skb_segment(struct sk_bu
BUG_ON(i >= nfrags);
*frag = skb_shinfo(skb)->frags[i];
- get_page(frag->page);
+ skb_get_page(nskb, frag->page);
size = frag->size;
if (pos < offset) {
@@ -2483,6 +2613,7 @@ EXPORT_SYMBOL(__pskb_pull_tail);
EXPORT_SYMBOL(__alloc_skb);
EXPORT_SYMBOL(__netdev_alloc_skb);
EXPORT_SYMBOL(__netdev_alloc_page);
+EXPORT_SYMBOL(__netdev_free_page);
EXPORT_SYMBOL(skb_add_rx_frag);
EXPORT_SYMBOL(pskb_copy);
EXPORT_SYMBOL(pskb_expand_head);
Index: linux-2.6/include/linux/mm_types.h
===================================================================
--- linux-2.6.orig/include/linux/mm_types.h
+++ linux-2.6/include/linux/mm_types.h
@@ -71,6 +71,7 @@ struct page {
pgoff_t index; /* Our offset within mapping. */
void *freelist; /* SLUB: freelist req. slab lock */
int reserve; /* page_alloc: page is a reserve page */
+ atomic_t frag_count; /* skb fragment use count */
};
struct list_head lru; /* Pageout list, eg. active_list
* protected by zone->lru_lock !
--
^ permalink raw reply
* [PATCH 13/33] net: wrap sk->sk_backlog_rcv()
From: Peter Zijlstra @ 2007-10-30 16:04 UTC (permalink / raw)
To: Linus Torvalds, Andrew Morton, linux-kernel, linux-mm, netdev,
trond.myklebust
Cc: Peter Zijlstra
In-Reply-To: <20071030160401.296770000@chello.nl>
[-- Attachment #1: net-backlog.patch --]
[-- Type: text/plain, Size: 2412 bytes --]
Wrap calling sk->sk_backlog_rcv() in a function. This will allow extending the
generic sk_backlog_rcv behaviour.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
include/net/sock.h | 5 +++++
net/core/sock.c | 4 ++--
net/ipv4/tcp.c | 2 +-
net/ipv4/tcp_timer.c | 2 +-
4 files changed, 9 insertions(+), 4 deletions(-)
Index: linux-2.6/include/net/sock.h
===================================================================
--- linux-2.6.orig/include/net/sock.h
+++ linux-2.6/include/net/sock.h
@@ -485,6 +485,11 @@ static inline void sk_add_backlog(struct
skb->next = NULL;
}
+static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
+{
+ return sk->sk_backlog_rcv(sk, skb);
+}
+
#define sk_wait_event(__sk, __timeo, __condition) \
({ int __rc; \
release_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
@@ -320,7 +320,7 @@ int sk_receive_skb(struct sock *sk, stru
*/
mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_);
- rc = sk->sk_backlog_rcv(sk, skb);
+ rc = sk_backlog_rcv(sk, skb);
mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
} else
@@ -1312,7 +1312,7 @@ static void __release_sock(struct sock *
struct sk_buff *next = skb->next;
skb->next = NULL;
- sk->sk_backlog_rcv(sk, skb);
+ sk_backlog_rcv(sk, skb);
/*
* We are in process context here with softirqs
Index: linux-2.6/net/ipv4/tcp.c
===================================================================
--- linux-2.6.orig/net/ipv4/tcp.c
+++ linux-2.6/net/ipv4/tcp.c
@@ -1134,7 +1134,7 @@ static void tcp_prequeue_process(struct
* necessary */
local_bh_disable();
while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
- sk->sk_backlog_rcv(sk, skb);
+ sk_backlog_rcv(sk, skb);
local_bh_enable();
/* Clear memory counter. */
Index: linux-2.6/net/ipv4/tcp_timer.c
===================================================================
--- linux-2.6.orig/net/ipv4/tcp_timer.c
+++ linux-2.6/net/ipv4/tcp_timer.c
@@ -196,7 +196,7 @@ static void tcp_delack_timer(unsigned lo
NET_INC_STATS_BH(LINUX_MIB_TCPSCHEDULERFAILED);
while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
- sk->sk_backlog_rcv(sk, skb);
+ sk_backlog_rcv(sk, skb);
tp->ucopy.memory = 0;
}
--
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox