* [PATCH 10/17] netvm: Allow skb allocation to use PFMEMALLOC reserves
From: Mel Gorman @ 2012-05-10 13:45 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, LKML, David Miller, Neil Brown,
Peter Zijlstra, Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336657510-24378-1-git-send-email-mgorman@suse.de>
Change the skb allocation API to indicate RX usage and use this to fall
back to the PFMEMALLOC reserve when needed. SKBs allocated from the
reserve are tagged in skb->pfmemalloc. If an SKB is allocated from
the reserve and the socket is later found to be unrelated to page
reclaim, the packet is dropped so that the memory remains available
for page reclaim. Network protocols are expected to recover from this
packet loss.
[a.p.zijlstra@chello.nl: Ideas taken from various patches]
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
include/linux/gfp.h | 3 ++
include/linux/skbuff.h | 17 +++++++--
include/net/sock.h | 6 ++++
mm/internal.h | 3 --
net/core/filter.c | 8 +++++
net/core/skbuff.c | 94 ++++++++++++++++++++++++++++++++++++++++--------
net/core/sock.c | 4 +++
7 files changed, 114 insertions(+), 21 deletions(-)
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 94af4a2..83cd7b6 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -385,6 +385,9 @@ void drain_local_pages(void *dummy);
*/
extern gfp_t gfp_allowed_mask;
+/* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */
+bool gfp_pfmemalloc_allowed(gfp_t gfp_mask);
+
extern void pm_restrict_gfp_mask(void);
extern void pm_restore_gfp_mask(void);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 775292a..91dd366 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -465,6 +465,7 @@ struct sk_buff {
#ifdef CONFIG_IPV6_NDISC_NODETYPE
__u8 ndisc_nodetype:2;
#endif
+ __u8 pfmemalloc:1;
__u8 ooo_okay:1;
__u8 l4_rxhash:1;
__u8 wifi_acked_valid:1;
@@ -504,6 +505,15 @@ struct sk_buff {
#include <linux/slab.h>
+#define SKB_ALLOC_FCLONE 0x01
+#define SKB_ALLOC_RX 0x02
+
+/* Returns true if the skb was allocated from PFMEMALLOC reserves */
+static inline bool skb_pfmemalloc(struct sk_buff *skb)
+{
+ return unlikely(skb->pfmemalloc);
+}
+
/*
* skb might have a dst pointer attached, refcounted or not.
* _skb_refdst low order bit is set if refcount was _not_ taken
@@ -561,7 +571,7 @@ extern void kfree_skb(struct sk_buff *skb);
extern void consume_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);
extern struct sk_buff *build_skb(void *data);
static inline struct sk_buff *alloc_skb(unsigned int size,
gfp_t priority)
@@ -572,7 +582,7 @@ static inline struct sk_buff *alloc_skb(unsigned int size,
static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
gfp_t priority)
{
- return __alloc_skb(size, priority, 1, NUMA_NO_NODE);
+ return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE);
}
extern void skb_recycle(struct sk_buff *skb);
@@ -1679,7 +1689,8 @@ static inline void __skb_queue_purge(struct sk_buff_head *list)
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, NUMA_NO_NODE);
if (likely(skb))
skb_reserve(skb, NET_SKB_PAD);
return skb;
diff --git a/include/net/sock.h b/include/net/sock.h
index 4da0acb..e6a4248 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -645,6 +645,12 @@ static inline int sock_flag(struct sock *sk, enum sock_flags flag)
return test_bit(flag, &sk->sk_flags);
}
+extern atomic_t memalloc_socks;
+static inline int sk_memalloc_socks(void)
+{
+ return atomic_read(&memalloc_socks);
+}
+
static inline gfp_t sk_allocation(struct sock *sk, gfp_t gfp_mask)
{
return gfp_mask | (sk->sk_allocation & __GFP_MEMALLOC);
diff --git a/mm/internal.h b/mm/internal.h
index bff60d8..2189af4 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -239,9 +239,6 @@ static inline struct page *mem_map_next(struct page *iter,
#define __paginginit __init
#endif
-/* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */
-bool gfp_pfmemalloc_allowed(gfp_t gfp_mask);
-
/* Memory initialisation debug and verification */
enum mminit_level {
MMINIT_WARNING,
diff --git a/net/core/filter.c b/net/core/filter.c
index 6f755cc..bc620e5 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -82,6 +82,14 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
int err;
struct sk_filter *filter;
+ /*
+ * If the skb was allocated from pfmemalloc reserves, only
+ * allow SOCK_MEMALLOC sockets to use it as this socket is
+ * helping free memory
+ */
+ if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC))
+ return -ENOMEM;
+
err = security_sock_rcv_skb(sk, skb);
if (err)
return err;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e598400..74c2ff2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -146,6 +146,43 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
BUG();
}
+
+/*
+ * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells
+ * the caller if emergency pfmemalloc reserves are being used. If it is and
+ * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves
+ * may be used. Otherwise, the packet data may be discarded until enough
+ * memory is free
+ */
+#define kmalloc_reserve(size, gfp, node, pfmemalloc) \
+ __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc)
+void *__kmalloc_reserve(size_t size, gfp_t flags, int node, unsigned long ip,
+ bool *pfmemalloc)
+{
+ void *obj;
+ bool ret_pfmemalloc = false;
+
+ /*
+ * Try a regular allocation, when that fails and we're not entitled
+ * to the reserves, fail.
+ */
+ obj = kmalloc_node_track_caller(size,
+ flags | __GFP_NOMEMALLOC | __GFP_NOWARN,
+ node);
+ if (obj || !(gfp_pfmemalloc_allowed(flags)))
+ goto out;
+
+ /* Try again but now we are using pfmemalloc reserves */
+ ret_pfmemalloc = true;
+ obj = kmalloc_node_track_caller(size, flags, node);
+
+out:
+ if (pfmemalloc)
+ *pfmemalloc = ret_pfmemalloc;
+
+ return obj;
+}
+
/* Allocate a new skbuff. We do this ourselves so we can fill in a few
* 'private' fields and also do memory statistics to find all the
* [BEEP] leaks.
@@ -156,8 +193,10 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
* __alloc_skb - allocate a network buffer
* @size: size to allocate
* @gfp_mask: allocation mask
- * @fclone: allocate from fclone cache instead of head cache
- * and allocate a cloned (child) skb
+ * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache
+ * instead of head cache and allocate a cloned (child) skb.
+ * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for
+ * allocations in case the data is required for writeback
* @node: numa node to allocate memory on
*
* Allocate a new &sk_buff. The returned buffer has no headroom and a
@@ -168,14 +207,19 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
* %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;
+ bool pfmemalloc;
+
+ cache = (flags & SKB_ALLOC_FCLONE)
+ ? skbuff_fclone_cache : skbuff_head_cache;
- cache = fclone ? skbuff_fclone_cache : skbuff_head_cache;
+ if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX))
+ gfp_mask |= __GFP_MEMALLOC;
/* Get the HEAD */
skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node);
@@ -190,7 +234,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
*/
size = SKB_DATA_ALIGN(size);
size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
- data = kmalloc_node_track_caller(size, gfp_mask, node);
+ data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc);
if (!data)
goto nodata;
/* kmalloc(size) might give us more room than requested.
@@ -208,6 +252,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
memset(skb, 0, offsetof(struct sk_buff, tail));
/* Account for allocated memory : skb + skb->head */
skb->truesize = SKB_TRUESIZE(size);
+ skb->pfmemalloc = pfmemalloc;
atomic_set(&skb->users, 1);
skb->head = data;
skb->data = data;
@@ -223,7 +268,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
atomic_set(&shinfo->dataref, 1);
kmemcheck_annotate_variable(shinfo->destructor_arg);
- if (fclone) {
+ if (flags & SKB_ALLOC_FCLONE) {
struct sk_buff *child = skb + 1;
atomic_t *fclone_ref = (atomic_t *) (child + 1);
@@ -233,6 +278,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
atomic_set(fclone_ref, 1);
child->fclone = SKB_FCLONE_UNAVAILABLE;
+ child->pfmemalloc = pfmemalloc;
}
out:
return skb;
@@ -310,7 +356,8 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
{
struct sk_buff *skb;
- skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE);
+ skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask,
+ SKB_ALLOC_RX, NUMA_NO_NODE);
if (likely(skb)) {
skb_reserve(skb, NET_SKB_PAD);
skb->dev = dev;
@@ -605,6 +652,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
#if IS_ENABLED(CONFIG_IP_VS)
new->ipvs_property = old->ipvs_property;
#endif
+ new->pfmemalloc = old->pfmemalloc;
new->protocol = old->protocol;
new->mark = old->mark;
new->skb_iif = old->skb_iif;
@@ -763,6 +811,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
n->fclone = SKB_FCLONE_CLONE;
atomic_inc(fclone_ref);
} else {
+ if (skb_pfmemalloc(skb))
+ gfp_mask |= __GFP_MEMALLOC;
+
n = kmem_cache_alloc(skbuff_head_cache, gfp_mask);
if (!n)
return NULL;
@@ -799,6 +850,13 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
}
+static inline int skb_alloc_rx_flag(const struct sk_buff *skb)
+{
+ if (skb_pfmemalloc((struct sk_buff *)skb))
+ return SKB_ALLOC_RX;
+ return 0;
+}
+
/**
* skb_copy - create private copy of an sk_buff
* @skb: buffer to copy
@@ -820,7 +878,8 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
{
int headerlen = skb_headroom(skb);
unsigned int size = (skb_end_pointer(skb) - skb->head) + skb->data_len;
- struct sk_buff *n = alloc_skb(size, gfp_mask);
+ struct sk_buff *n = __alloc_skb(size, gfp_mask,
+ skb_alloc_rx_flag(skb), NUMA_NO_NODE);
if (!n)
return NULL;
@@ -855,7 +914,8 @@ EXPORT_SYMBOL(skb_copy);
struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask)
{
unsigned int size = skb_headlen(skb) + headroom;
- struct sk_buff *n = alloc_skb(size, gfp_mask);
+ struct sk_buff *n = __alloc_skb(size, gfp_mask,
+ skb_alloc_rx_flag(skb), NUMA_NO_NODE);
if (!n)
goto out;
@@ -952,8 +1012,10 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
goto adjust_others;
}
- data = kmalloc(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
- gfp_mask);
+ if (skb_pfmemalloc(skb))
+ gfp_mask |= __GFP_MEMALLOC;
+ data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
+ gfp_mask, NUMA_NO_NODE, NULL);
if (!data)
goto nodata;
size = SKB_WITH_OVERHEAD(ksize(data));
@@ -1062,8 +1124,9 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
/*
* 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),
+ NUMA_NO_NODE);
int oldheadroom = skb_headroom(skb);
int head_copy_len, head_copy_off;
int off;
@@ -2729,8 +2792,9 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
skb_release_head_state(nskb);
__skb_push(nskb, doffset);
} else {
- nskb = alloc_skb(hsize + doffset + headroom,
- GFP_ATOMIC);
+ nskb = __alloc_skb(hsize + doffset + headroom,
+ GFP_ATOMIC, skb_alloc_rx_flag(skb),
+ NUMA_NO_NODE);
if (unlikely(!nskb))
goto err;
diff --git a/net/core/sock.c b/net/core/sock.c
index b0f0613..cd2ad2b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -266,6 +266,8 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
EXPORT_SYMBOL(sysctl_optmem_max);
+atomic_t memalloc_socks __read_mostly;
+
/**
* sk_set_memalloc - sets %SOCK_MEMALLOC
* @sk: socket to set it on
@@ -278,6 +280,7 @@ void sk_set_memalloc(struct sock *sk)
{
sock_set_flag(sk, SOCK_MEMALLOC);
sk->sk_allocation |= __GFP_MEMALLOC;
+ atomic_inc(&memalloc_socks);
}
EXPORT_SYMBOL_GPL(sk_set_memalloc);
@@ -285,6 +288,7 @@ void sk_clear_memalloc(struct sock *sk)
{
sock_reset_flag(sk, SOCK_MEMALLOC);
sk->sk_allocation &= ~__GFP_MEMALLOC;
+ atomic_dec(&memalloc_socks);
}
EXPORT_SYMBOL_GPL(sk_clear_memalloc);
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 11/17] netvm: Propagate page->pfmemalloc to skb
From: Mel Gorman @ 2012-05-10 13:45 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, LKML, David Miller, Neil Brown,
Peter Zijlstra, Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336657510-24378-1-git-send-email-mgorman@suse.de>
The skb->pfmemalloc flag gets set to true iff during the slab
allocation of data in __alloc_skb that the the PFMEMALLOC reserves
were used. If the packet is fragmented, it is possible that pages
will be allocated from the PFMEMALLOC reserve without propagating
this information to the skb. This patch propagates page->pfmemalloc
from pages allocated for fragments to the skb.
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
include/linux/skbuff.h | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 91dd366..ed7cc48 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1229,6 +1229,17 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i,
{
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+ /*
+ * Propagate page->pfmemalloc to the skb if we can. The problem is
+ * that not all callers have unique ownership of the page. If
+ * pfmemalloc is set, we check the mapping as a mapping implies
+ * page->index is set (index and pfmemalloc share space).
+ * If it's a valid mapping, we cannot use page->pfmemalloc but we
+ * do not lose pfmemalloc information as the pages would not be
+ * allocated using __GFP_MEMALLOC.
+ */
+ if (page->pfmemalloc && !page->mapping)
+ skb->pfmemalloc = true;
frag->page.p = page;
frag->page_offset = off;
skb_frag_size_set(frag, size);
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 12/17] netvm: Propagate page->pfmemalloc from netdev_alloc_page to skb
From: Mel Gorman @ 2012-05-10 13:45 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, LKML, David Miller, Neil Brown,
Peter Zijlstra, Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336657510-24378-1-git-send-email-mgorman@suse.de>
The skb->pfmemalloc flag gets set to true iff during the slab
allocation of data in __alloc_skb that the the PFMEMALLOC reserves
were used. If page splitting is used, it is possible that pages will
be allocated from the PFMEMALLOC reserve without propagating this
information to the skb. This patch propagates page->pfmemalloc from
pages allocated for fragments to the skb.
It works by reintroducing and expanding the netdev_alloc_page() API
to take an skb. If the page was allocated from pfmemalloc reserves,
it is automatically copied. If the driver allocates the page before
the skb, it should call propagate_pfmemalloc_skb() after the skb is
allocated to ensure the flag is copied properly.
Failure to do so is not critical. The resulting driver may perform
slower if it is used for swap-over-NBD or swap-over-NFS but it should
not result in failure.
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
drivers/net/ethernet/chelsio/cxgb4/sge.c | 2 +-
drivers/net/ethernet/chelsio/cxgb4vf/sge.c | 2 +-
drivers/net/ethernet/intel/igb/igb_main.c | 2 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +-
drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 +-
drivers/net/usb/cdc-phonet.c | 2 +-
drivers/usb/gadget/f_phonet.c | 2 +-
include/linux/skbuff.h | 55 +++++++++++++++++++++
8 files changed, 63 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 2dae795..05f02b3 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -528,7 +528,7 @@ static unsigned int refill_fl(struct adapter *adap, struct sge_fl *q, int n,
#endif
while (n--) {
- pg = alloc_page(gfp);
+ pg = __netdev_alloc_page(gfp, NULL);
if (unlikely(!pg)) {
q->alloc_failed++;
break;
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
index 0bd585b..e8a372e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -653,7 +653,7 @@ static unsigned int refill_fl(struct adapter *adapter, struct sge_fl *fl,
alloc_small_pages:
while (n--) {
- page = alloc_page(gfp | __GFP_NOWARN | __GFP_COLD);
+ page = __netdev_alloc_page(gfp | __GFP_NOWARN, NULL);
if (unlikely(!page)) {
fl->alloc_failed++;
break;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 5ec3159..9c2d7f6 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -6229,7 +6229,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
return true;
if (!page) {
- page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+ page = __netdev_alloc_page(GFP_ATOMIC, bi->skb);
bi->page = page;
if (unlikely(!page)) {
rx_ring->rx_stats.alloc_failed++;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a7f3cd8..a092486 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1126,7 +1126,7 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring,
/* alloc new page for storage */
if (likely(!page)) {
- page = alloc_pages(GFP_ATOMIC | __GFP_COLD,
+ page = __netdev_alloc_pages(GFP_ATOMIC, bi->skb,
ixgbe_rx_pg_order(rx_ring));
if (unlikely(!page)) {
rx_ring->rx_stats.alloc_rx_page_failed++;
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 307611a..4f1c14f 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -369,7 +369,7 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter,
if (!bi->page_dma &&
(adapter->flags & IXGBE_FLAG_RX_PS_ENABLED)) {
if (!bi->page) {
- bi->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+ bi->page = __netdev_alloc_page(GFP_ATOMIC, NULL);
if (!bi->page) {
adapter->alloc_rx_page_failed++;
goto no_buffers;
@@ -403,6 +403,7 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter,
*/
skb_reserve(skb, NET_IP_ALIGN);
+ propagate_pfmemalloc_skb(bi->page_dma, skb);
bi->skb = skb;
}
if (!bi->dma) {
diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c
index 3e41b00..5d46473 100644
--- a/drivers/net/usb/cdc-phonet.c
+++ b/drivers/net/usb/cdc-phonet.c
@@ -130,7 +130,7 @@ static int rx_submit(struct usbpn_dev *pnd, struct urb *req, gfp_t gfp_flags)
struct page *page;
int err;
- page = alloc_page(gfp_flags);
+ page = __netdev_alloc_page(gfp_flags | __GFP_NOMEMALLOC, NULL);
if (!page)
return -ENOMEM;
diff --git a/drivers/usb/gadget/f_phonet.c b/drivers/usb/gadget/f_phonet.c
index 965a629..19adb15 100644
--- a/drivers/usb/gadget/f_phonet.c
+++ b/drivers/usb/gadget/f_phonet.c
@@ -301,7 +301,7 @@ pn_rx_submit(struct f_phonet *fp, struct usb_request *req, gfp_t gfp_flags)
struct page *page;
int err;
- page = alloc_page(gfp_flags);
+ page = __netdev_alloc_page(gfp_flags | __GFP_NOMEMALLOC, NULL);
if (!page)
return -ENOMEM;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ed7cc48..28c3de7 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1747,6 +1747,61 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC);
}
+/*
+ * __netdev_alloc_page - allocate a page for ps-rx on a specific device
+ * @gfp_mask: alloc_pages_node mask. Set __GFP_NOMEMALLOC if not for network packet RX
+ * @skb: skb to set pfmemalloc on if __GFP_MEMALLOC is used
+ * @order: size of the allocation
+ *
+ * Allocate a new page. dev currently unused.
+ *
+ * %NULL is returned if there is no free memory.
+*/
+static inline struct page *__netdev_alloc_pages(gfp_t gfp_mask,
+ struct sk_buff *skb,
+ unsigned int order)
+{
+ struct page *page;
+
+ gfp_mask |= __GFP_COLD;
+
+ if (!(gfp_mask & __GFP_NOMEMALLOC))
+ gfp_mask |= __GFP_MEMALLOC;
+
+ page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
+ if (skb && page && page->pfmemalloc)
+ skb->pfmemalloc = true;
+
+ return page;
+}
+
+/**
+ * __netdev_alloc_page - allocate a page for ps-rx on a specific device
+ * @gfp_mask: alloc_pages_node mask. Set __GFP_NOMEMALLOC if not for network packet RX
+ * @skb: skb to set pfmemalloc on if __GFP_MEMALLOC is used
+ *
+ * Allocate a new page. dev currently unused.
+ *
+ * %NULL is returned if there is no free memory.
+ */
+static inline struct page *__netdev_alloc_page(gfp_t gfp_mask,
+ struct sk_buff *skb)
+{
+ return __netdev_alloc_pages(gfp_mask, skb, 0);
+}
+
+/**
+ * propagate_pfmemalloc_skb - Propagate pfmemalloc if skb is allocated after RX page
+ * @page: The page that was allocated from netdev_alloc_page
+ * @skb: The skb that may need pfmemalloc set
+ */
+static inline void propagate_pfmemalloc_skb(struct page *page,
+ struct sk_buff *skb)
+{
+ if (page && page->pfmemalloc)
+ skb->pfmemalloc = true;
+}
+
/**
* skb_frag_page - retrieve the page refered to by a paged fragment
* @frag: the paged fragment
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 13/17] netvm: Set PF_MEMALLOC as appropriate during SKB processing
From: Mel Gorman @ 2012-05-10 13:45 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, LKML, David Miller, Neil Brown,
Peter Zijlstra, Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336657510-24378-1-git-send-email-mgorman@suse.de>
In order to make sure pfmemalloc packets receive all memory
needed to proceed, ensure processing of pfmemalloc SKBs happens
under PF_MEMALLOC. This is limited to a subset of protocols that
are expected to be used for writing to swap. Taps are not allowed to
use PF_MEMALLOC as these are expected to communicate with userspace
processes which could be paged out.
[a.p.zijlstra@chello.nl: Ideas taken from various patches]
[jslaby@suse.cz: Lock imbalance fix]
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
include/net/sock.h | 5 +++++
net/core/dev.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++------
net/core/sock.c | 16 ++++++++++++++++
3 files changed, 67 insertions(+), 6 deletions(-)
diff --git a/include/net/sock.h b/include/net/sock.h
index e6a4248..7f04aa8 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -729,8 +729,13 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s
return 0;
}
+extern int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
+
static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
+ if (skb_pfmemalloc(skb))
+ return __sk_backlog_rcv(sk, skb);
+
return sk->sk_backlog_rcv(sk, skb);
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 9bb8f87..e78273e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3173,6 +3173,23 @@ void netdev_rx_handler_unregister(struct net_device *dev)
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
+/*
+ * Limit the use of PFMEMALLOC reserves to those protocols that implement
+ * the special handling of PFMEMALLOC skbs.
+ */
+static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
+{
+ switch (skb->protocol) {
+ case __constant_htons(ETH_P_ARP):
+ case __constant_htons(ETH_P_IP):
+ case __constant_htons(ETH_P_IPV6):
+ case __constant_htons(ETH_P_8021Q):
+ return true;
+ default:
+ return false;
+ }
+}
+
static int __netif_receive_skb(struct sk_buff *skb)
{
struct packet_type *ptype, *pt_prev;
@@ -3182,14 +3199,27 @@ static int __netif_receive_skb(struct sk_buff *skb)
bool deliver_exact = false;
int ret = NET_RX_DROP;
__be16 type;
+ unsigned long pflags = current->flags;
net_timestamp_check(!netdev_tstamp_prequeue, skb);
trace_netif_receive_skb(skb);
+ /*
+ * PFMEMALLOC skbs are special, they should
+ * - be delivered to SOCK_MEMALLOC sockets only
+ * - stay away from userspace
+ * - have bounded memory usage
+ *
+ * Use PF_MEMALLOC as this saves us from propagating the allocation
+ * context down to all allocation sites.
+ */
+ if (skb_pfmemalloc(skb))
+ current->flags |= PF_MEMALLOC;
+
/* if we've gotten here through NAPI, check netpoll */
if (netpoll_receive_skb(skb))
- return NET_RX_DROP;
+ goto out;
if (!skb->skb_iif)
skb->skb_iif = skb->dev->ifindex;
@@ -3210,7 +3240,7 @@ another_round:
if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
skb = vlan_untag(skb);
if (unlikely(!skb))
- goto out;
+ goto unlock;
}
#ifdef CONFIG_NET_CLS_ACT
@@ -3220,6 +3250,9 @@ another_round:
}
#endif
+ if (skb_pfmemalloc(skb))
+ goto skip_taps;
+
list_for_each_entry_rcu(ptype, &ptype_all, list) {
if (!ptype->dev || ptype->dev == skb->dev) {
if (pt_prev)
@@ -3228,13 +3261,17 @@ another_round:
}
}
+skip_taps:
#ifdef CONFIG_NET_CLS_ACT
skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
if (!skb)
- goto out;
+ goto unlock;
ncls:
#endif
+ if (skb_pfmemalloc(skb) && !skb_pfmemalloc_protocol(skb))
+ goto drop;
+
rx_handler = rcu_dereference(skb->dev->rx_handler);
if (vlan_tx_tag_present(skb)) {
if (pt_prev) {
@@ -3244,7 +3281,7 @@ ncls:
if (vlan_do_receive(&skb, !rx_handler))
goto another_round;
else if (unlikely(!skb))
- goto out;
+ goto unlock;
}
if (rx_handler) {
@@ -3254,7 +3291,7 @@ ncls:
}
switch (rx_handler(&skb)) {
case RX_HANDLER_CONSUMED:
- goto out;
+ goto unlock;
case RX_HANDLER_ANOTHER:
goto another_round;
case RX_HANDLER_EXACT:
@@ -3284,6 +3321,7 @@ ncls:
if (pt_prev) {
ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
} else {
+drop:
atomic_long_inc(&skb->dev->rx_dropped);
kfree_skb(skb);
/* Jamal, now you will not able to escape explaining
@@ -3292,8 +3330,10 @@ ncls:
ret = NET_RX_DROP;
}
-out:
+unlock:
rcu_read_unlock();
+out:
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
return ret;
}
diff --git a/net/core/sock.c b/net/core/sock.c
index cd2ad2b..9ad1ed9 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -292,6 +292,22 @@ void sk_clear_memalloc(struct sock *sk)
}
EXPORT_SYMBOL_GPL(sk_clear_memalloc);
+int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
+{
+ int ret;
+ unsigned long pflags = current->flags;
+
+ /* these should have been dropped before queueing */
+ BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));
+
+ current->flags |= PF_MEMALLOC;
+ ret = sk->sk_backlog_rcv(sk, skb);
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
+
+ return ret;
+}
+EXPORT_SYMBOL(__sk_backlog_rcv);
+
#if defined(CONFIG_CGROUPS)
#if !defined(CONFIG_NET_CLS_CGROUP)
int net_cls_subsys_id = -1;
--
1.7.9.2
^ permalink raw reply related
* [PATCH 14/17] mm: Micro-optimise slab to avoid a function call
From: Mel Gorman @ 2012-05-10 13:45 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, LKML, David Miller, Neil Brown,
Peter Zijlstra, Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336657510-24378-1-git-send-email-mgorman@suse.de>
Getting and putting objects in SLAB currently requires a function call
but the bulk of the work is related to PFMEMALLOC reserves which are
only consumed when network-backed storage is critical. Use an inline
function to determine if the function call is required.
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
mm/slab.c | 28 ++++++++++++++++++++++++++--
1 file changed, 26 insertions(+), 2 deletions(-)
diff --git a/mm/slab.c b/mm/slab.c
index 8e660b3..5b2ae1c 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -117,6 +117,8 @@
#include <linux/memory.h>
#include <linux/prefetch.h>
+#include <net/sock.h>
+
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
@@ -1012,7 +1014,7 @@ static void check_ac_pfmemalloc(struct kmem_cache *cachep,
pfmemalloc_active = false;
}
-static void *ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
+static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
gfp_t flags, bool force_refill)
{
int i;
@@ -1059,7 +1061,20 @@ static void *ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
return objp;
}
-static void ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
+static inline void *ac_get_obj(struct kmem_cache *cachep,
+ struct array_cache *ac, gfp_t flags, bool force_refill)
+{
+ void *objp;
+
+ if (unlikely(sk_memalloc_socks()))
+ objp = __ac_get_obj(cachep, ac, flags, force_refill);
+ else
+ objp = ac->entry[--ac->avail];
+
+ return objp;
+}
+
+static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
void *objp)
{
if (unlikely(pfmemalloc_active)) {
@@ -1069,6 +1084,15 @@ static void ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
set_obj_pfmemalloc(&objp);
}
+ return objp;
+}
+
+static inline void ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
+ void *objp)
+{
+ if (unlikely(sk_memalloc_socks()))
+ objp = __ac_put_obj(cachep, ac, objp);
+
ac->entry[ac->avail++] = objp;
}
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 15/17] nbd: Set SOCK_MEMALLOC for access to PFMEMALLOC reserves
From: Mel Gorman @ 2012-05-10 13:45 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, LKML, David Miller, Neil Brown,
Peter Zijlstra, Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336657510-24378-1-git-send-email-mgorman@suse.de>
Set SOCK_MEMALLOC on the NBD socket to allow access to PFMEMALLOC
reserves so pages backed by NBD, particularly if swap related, can
be cleaned to prevent the machine being deadlocked. It is still
possible that the PFMEMALLOC reserves get depleted resulting in
deadlock but this can be resolved by the administrator by increasing
min_free_kbytes.
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
drivers/block/nbd.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 061427a75d..76bc96f 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -154,6 +154,7 @@ static int sock_xmit(struct nbd_device *nbd, int send, void *buf, int size,
struct msghdr msg;
struct kvec iov;
sigset_t blocked, oldset;
+ unsigned long pflags = current->flags;
if (unlikely(!sock)) {
dev_err(disk_to_dev(nbd->disk),
@@ -167,8 +168,9 @@ static int sock_xmit(struct nbd_device *nbd, int send, void *buf, int size,
siginitsetinv(&blocked, sigmask(SIGKILL));
sigprocmask(SIG_SETMASK, &blocked, &oldset);
+ current->flags |= PF_MEMALLOC;
do {
- sock->sk->sk_allocation = GFP_NOIO;
+ sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC;
iov.iov_base = buf;
iov.iov_len = size;
msg.msg_name = NULL;
@@ -214,6 +216,7 @@ static int sock_xmit(struct nbd_device *nbd, int send, void *buf, int size,
} while (size > 0);
sigprocmask(SIG_SETMASK, &oldset, NULL);
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
return result;
}
@@ -405,6 +408,7 @@ static int nbd_do_it(struct nbd_device *nbd)
BUG_ON(nbd->magic != NBD_MAGIC);
+ sk_set_memalloc(nbd->sock->sk);
nbd->pid = task_pid_nr(current);
ret = device_create_file(disk_to_dev(nbd->disk), &pid_attr);
if (ret) {
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 16/17] mm: Throttle direct reclaimers if PF_MEMALLOC reserves are low and swap is backed by network storage
From: Mel Gorman @ 2012-05-10 13:45 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, LKML, David Miller, Neil Brown,
Peter Zijlstra, Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336657510-24378-1-git-send-email-mgorman@suse.de>
If swap is backed by network storage such as NBD, there is a risk
that a large number of reclaimers can hang the system by consuming
all PF_MEMALLOC reserves. To avoid these hangs, the administrator
must tune min_free_kbytes in advance which is a bit fragile.
This patch throttles direct reclaimers if half the PF_MEMALLOC reserves
are in use. If the system is routinely getting throttled the system
administrator can increase min_free_kbytes so degradation is smoother
but the system will keep running.
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
include/linux/mmzone.h | 1 +
mm/page_alloc.c | 1 +
mm/vmscan.c | 128 +++++++++++++++++++++++++++++++++++++++++++++---
3 files changed, 122 insertions(+), 8 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index dff7115..e6b733d 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -663,6 +663,7 @@ typedef struct pglist_data {
range, including holes */
int node_id;
wait_queue_head_t kswapd_wait;
+ wait_queue_head_t pfmemalloc_wait;
struct task_struct *kswapd;
int kswapd_max_order;
enum zone_type classzone_idx;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e225a7c..b9eb64a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4326,6 +4326,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
pgdat_resize_init(pgdat);
pgdat->nr_zones = 0;
init_waitqueue_head(&pgdat->kswapd_wait);
+ init_waitqueue_head(&pgdat->pfmemalloc_wait);
pgdat->kswapd_max_order = 0;
pgdat_page_cgroup_init(pgdat);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 33dc256..97c766f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2431,6 +2431,80 @@ out:
return 0;
}
+static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
+{
+ struct zone *zone;
+ unsigned long pfmemalloc_reserve = 0;
+ unsigned long free_pages = 0;
+ int i;
+ bool wmark_ok;
+
+ for (i = 0; i <= ZONE_NORMAL; i++) {
+ zone = &pgdat->node_zones[i];
+ pfmemalloc_reserve += min_wmark_pages(zone);
+ free_pages += zone_page_state(zone, NR_FREE_PAGES);
+ }
+
+ wmark_ok = free_pages > pfmemalloc_reserve / 2;
+
+ /* kswapd must be awake if processes are being throttled */
+ if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
+ pgdat->classzone_idx = min(pgdat->classzone_idx,
+ (enum zone_type)ZONE_NORMAL);
+ wake_up_interruptible(&pgdat->kswapd_wait);
+ }
+
+ return wmark_ok;
+}
+
+/*
+ * Throttle direct reclaimers if backing storage is backed by the network
+ * and the PFMEMALLOC reserve for the preferred node is getting dangerously
+ * depleted. kswapd will continue to make progress and wake the processes
+ * when the low watermark is reached
+ */
+static void throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
+ nodemask_t *nodemask)
+{
+ struct zone *zone;
+ int high_zoneidx = gfp_zone(gfp_mask);
+ pg_data_t *pgdat;
+
+ /*
+ * Kernel threads should not be throttled as they may be indirectly
+ * responsible for cleaning pages necessary for reclaim to make forward
+ * progress. kjournald for example may enter direct reclaim while
+ * committing a transaction where throttling it could forcing other
+ * processes to block on log_wait_commit().
+ */
+ if (current->flags & PF_KTHREAD)
+ return;
+
+ /* Check if the pfmemalloc reserves are ok */
+ first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
+ pgdat = zone->zone_pgdat;
+ if (pfmemalloc_watermark_ok(pgdat))
+ return;
+
+ /*
+ * If the caller cannot enter the filesystem, it's possible that it
+ * is due to the caller holding an FS lock or performing a journal
+ * transaction in the case of a filesystem like ext[3|4]. In this case,
+ * it is not safe to block on pfmemalloc_wait as kswapd could be
+ * blocked waiting on the same lock. Instead, throttle for up to a
+ * second before continuing.
+ */
+ if (!(gfp_mask & __GFP_FS)) {
+ wait_event_interruptible_timeout(pgdat->pfmemalloc_wait,
+ pfmemalloc_watermark_ok(pgdat), HZ);
+ return;
+ }
+
+ /* Throttle until kswapd wakes the process */
+ wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
+ pfmemalloc_watermark_ok(pgdat));
+}
+
unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask, nodemask_t *nodemask)
{
@@ -2449,6 +2523,15 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
.gfp_mask = sc.gfp_mask,
};
+ throttle_direct_reclaim(gfp_mask, zonelist, nodemask);
+
+ /*
+ * Do not enter reclaim if fatal signal is pending. 1 is returned so
+ * that the page allocator does not consider triggering OOM
+ */
+ if (fatal_signal_pending(current))
+ return 1;
+
trace_mm_vmscan_direct_reclaim_begin(order,
sc.may_writepage,
gfp_mask);
@@ -2598,8 +2681,13 @@ static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced_pages,
return balanced_pages >= (present_pages >> 2);
}
-/* is kswapd sleeping prematurely? */
-static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining,
+/*
+ * Prepare kswapd for sleeping. This verifies that there are no processes
+ * waiting in throttle_direct_reclaim() and that watermarks have been met.
+ *
+ * Returns true if kswapd is ready to sleep
+ */
+static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
int classzone_idx)
{
int i;
@@ -2608,7 +2696,21 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining,
/* If a direct reclaimer woke kswapd within HZ/10, it's premature */
if (remaining)
- return true;
+ return false;
+
+ /*
+ * There is a potential race between when kswapd checks its watermarks
+ * and a process gets throttled. There is also a potential race if
+ * processes get throttled, kswapd wakes, a large process exits therby
+ * balancing the zones that causes kswapd to miss a wakeup. If kswapd
+ * is going to sleep, no process should be sleeping on pfmemalloc_wait
+ * so wake them now if necessary. If necessary, processes will wake
+ * kswapd and get throttled again
+ */
+ if (waitqueue_active(&pgdat->pfmemalloc_wait)) {
+ wake_up(&pgdat->pfmemalloc_wait);
+ return false;
+ }
/* Check the watermark levels */
for (i = 0; i <= classzone_idx; i++) {
@@ -2641,9 +2743,9 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining,
* must be balanced
*/
if (order)
- return !pgdat_balanced(pgdat, balanced, classzone_idx);
+ return pgdat_balanced(pgdat, balanced, classzone_idx);
else
- return !all_zones_ok;
+ return all_zones_ok;
}
/*
@@ -2871,6 +2973,16 @@ loop_again:
}
}
+
+ /*
+ * If the low watermark is met there is no need for processes
+ * to be throttled on pfmemalloc_wait as they should not be
+ * able to safely make forward progress. Wake them
+ */
+ if (waitqueue_active(&pgdat->pfmemalloc_wait) &&
+ pfmemalloc_watermark_ok(pgdat))
+ wake_up(&pgdat->pfmemalloc_wait);
+
if (all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))
break; /* kswapd: all done */
/*
@@ -2971,7 +3083,7 @@ out:
}
/*
- * Return the order we were reclaiming at so sleeping_prematurely()
+ * Return the order we were reclaiming at so prepare_kswapd_sleep()
* makes a decision on the order we were last reclaiming at. However,
* if another caller entered the allocator slow path while kswapd
* was awake, order will remain at the higher level
@@ -2991,7 +3103,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
/* Try to sleep for a short interval */
- if (!sleeping_prematurely(pgdat, order, remaining, classzone_idx)) {
+ if (prepare_kswapd_sleep(pgdat, order, remaining, classzone_idx)) {
remaining = schedule_timeout(HZ/10);
finish_wait(&pgdat->kswapd_wait, &wait);
prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
@@ -3001,7 +3113,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
* After a short sleep, check if it was a premature sleep. If not, then
* go fully to sleep until explicitly woken up.
*/
- if (!sleeping_prematurely(pgdat, order, remaining, classzone_idx)) {
+ if (prepare_kswapd_sleep(pgdat, order, remaining, classzone_idx)) {
trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
/*
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 17/17] mm: Account for the number of times direct reclaimers get throttled
From: Mel Gorman @ 2012-05-10 13:45 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, LKML, David Miller, Neil Brown,
Peter Zijlstra, Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336657510-24378-1-git-send-email-mgorman@suse.de>
Under significant pressure when writing back to network-backed storage,
direct reclaimers may get throttled. This is expected to be a
short-lived event and the processes get woken up again but processes do
get stalled. This patch counts how many times such stalling occurs. It's
up to the administrator whether to reduce these stalls by increasing
min_free_kbytes.
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
include/linux/vm_event_item.h | 1 +
mm/vmscan.c | 3 +++
mm/vmstat.c | 1 +
3 files changed, 5 insertions(+)
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 06f8e38..57f7b10 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -30,6 +30,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
FOR_ALL_ZONES(PGSTEAL_DIRECT),
FOR_ALL_ZONES(PGSCAN_KSWAPD),
FOR_ALL_ZONES(PGSCAN_DIRECT),
+ PGSCAN_DIRECT_THROTTLE,
#ifdef CONFIG_NUMA
PGSCAN_ZONE_RECLAIM_FAILED,
#endif
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 97c766f..141ab5c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2486,6 +2486,9 @@ static void throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
if (pfmemalloc_watermark_ok(pgdat))
return;
+ /* Account for the throttling */
+ count_vm_event(PGSCAN_DIRECT_THROTTLE);
+
/*
* If the caller cannot enter the filesystem, it's possible that it
* is due to the caller holding an FS lock or performing a journal
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 7db1b9b..7861cbe 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -742,6 +742,7 @@ const char * const vmstat_text[] = {
TEXTS_FOR_ZONES("pgsteal_direct")
TEXTS_FOR_ZONES("pgscan_kswapd")
TEXTS_FOR_ZONES("pgscan_direct")
+ "pgscan_direct_throttle",
#ifdef CONFIG_NUMA
"zone_reclaim_failed",
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 07/17] mm: Ignore mempolicies when using ALLOC_NO_WATERMARK
From: Mel Gorman @ 2012-05-10 13:45 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, LKML, David Miller, Neil Brown,
Peter Zijlstra, Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336657510-24378-1-git-send-email-mgorman@suse.de>
The reserve is proportionally distributed over all !highmem zones
in the system. So we need to allow an emergency allocation access to
all zones. In order to do that we need to break out of any mempolicy
boundaries we might have.
In my opinion that does not break mempolicies as those are user
oriented and not system oriented. That is, system allocations are
not guaranteed to be within mempolicy boundaries. For instance IRQs
do not even have a mempolicy.
So breaking out of mempolicy boundaries for 'rare' emergency
allocations, which are always system allocations (as opposed to user)
is ok.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
mm/page_alloc.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 363ca90..e225a7c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2293,6 +2293,13 @@ rebalance:
/* Allocate without watermarks if the context allows */
if (alloc_flags & ALLOC_NO_WATERMARKS) {
+ /*
+ * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds
+ * the allocation is high priority and these type of
+ * allocations are system rather than user orientated
+ */
+ zonelist = node_zonelist(numa_node_id(), gfp_mask);
+
page = __alloc_pages_high_priority(gfp_mask, order,
zonelist, high_zoneidx, nodemask,
preferred_zone, migratetype);
--
1.7.9.2
^ permalink raw reply related
* [PATCH 00/12] Swap-over-NFS without deadlocking V4
From: Mel Gorman @ 2012-05-10 13:54 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, Linux-NFS, LKML, David Miller,
Trond Myklebust, Neil Brown, Christoph Hellwig, Peter Zijlstra,
Mike Christie, Eric B Munson, Mel Gorman
Changelog since V3
o Rebase to 3.4-rc5
o kmap pages for writing to swap (akpm)
o Move forward declaration to reduce chance of duplication (akpm)
Changelog since V2
o Nothing significant, just rebases. A radix tree lookup is replaced with
a linear search would be the biggest rebase artifact
This patch series is based on top of "Swap-over-NBD without deadlocking v9"
as it depends on the same reservation of PF_MEMALLOC reserves logic.
When a user or administrator requires swap for their application, they
create a swap partition and file, format it with mkswap and activate it with
swapon. In diskless systems this is not an option so if swap if required
then swapping over the network is considered. The two likely scenarios
are when blade servers are used as part of a cluster where the form factor
or maintenance costs do not allow the use of disks and thin clients.
The Linux Terminal Server Project recommends the use of the Network
Block Device (NBD) for swap but this is not always an option. There is
no guarantee that the network attached storage (NAS) device is running
Linux or supports NBD. However, it is likely that it supports NFS so there
are users that want support for swapping over NFS despite any performance
concern. Some distributions currently carry patches that support swapping
over NFS but it would be preferable to support it in the mainline kernel.
Patch 1 avoids a stream-specific deadlock that potentially affects TCP.
Patch 2 is a small modification to SELinux to avoid using PFMEMALLOC
reserves.
Patch 3 adds three helpers for filesystems to handle swap cache pages.
For example, page_file_mapping() returns page->mapping for
file-backed pages and the address_space of the underlying
swap file for swap cache pages.
Patch 4 adds two address_space_operations to allow a filesystem
to pin all metadata relevant to a swapfile in memory. Upon
successful activation, the swapfile is marked SWP_FILE and
the address space operation ->direct_IO is used for writing
and ->readpage for reading in swap pages.
Patch 5 notes that patch 3 is bolting
filesystem-specific-swapfile-support onto the side and that
the default handlers have different information to what
is available to the filesystem. This patch refactors the
code so that there are generic handlers for each of the new
address_space operations.
Patch 6 adds an API to allow a vector of kernel addresses to be
translated to struct pages and pinned for IO.
Patch 7 adds support for using highmem pages for swap by kmapping
the pages before calling the direct_IO handler.
Patch 8 updates NFS to use the helpers from patch 3 where necessary.
Patch 9 avoids setting PF_private on PG_swapcache pages within NFS.
Patch 10 implements the new swapfile-related address_space operations
for NFS and teaches the direct IO handler how to manage
kernel addresses.
Patch 11 prevents page allocator recursions in NFS by using GFP_NOIO
where appropriate.
Patch 12 fixes a NULL pointer dereference that occurs when using
swap-over-NFS.
With the patches applied, it is possible to mount a swapfile that is on an
NFS filesystem. Swap performance is not great with a swap stress test taking
roughly twice as long to complete than if the swap device was backed by NBD.
Documentation/filesystems/Locking | 13 ++++
Documentation/filesystems/vfs.txt | 12 +++
fs/nfs/Kconfig | 8 ++
fs/nfs/direct.c | 94 ++++++++++++++++--------
fs/nfs/file.c | 28 +++++--
fs/nfs/inode.c | 6 ++
fs/nfs/internal.h | 7 +-
fs/nfs/pagelist.c | 6 +-
fs/nfs/read.c | 6 +-
fs/nfs/write.c | 96 +++++++++++++++---------
include/linux/blk_types.h | 2 +
include/linux/fs.h | 8 ++
include/linux/highmem.h | 7 ++
include/linux/mm.h | 29 ++++++++
include/linux/nfs_fs.h | 4 +-
include/linux/pagemap.h | 5 ++
include/linux/sunrpc/xprt.h | 3 +
include/linux/swap.h | 8 ++
include/net/sock.h | 7 +-
mm/highmem.c | 12 +++
mm/memory.c | 52 +++++++++++++
mm/page_io.c | 145 +++++++++++++++++++++++++++++++++++++
mm/swap_state.c | 2 +-
mm/swapfile.c | 141 ++++++++++++++----------------------
net/caif/caif_socket.c | 2 +-
net/core/sock.c | 2 +-
net/ipv4/tcp_input.c | 12 +--
net/sctp/ulpevent.c | 2 +-
net/sunrpc/Kconfig | 5 ++
net/sunrpc/clnt.c | 2 +
net/sunrpc/sched.c | 7 +-
net/sunrpc/xprtsock.c | 53 ++++++++++++++
security/selinux/avc.c | 2 +-
33 files changed, 601 insertions(+), 187 deletions(-)
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply
* [PATCH 01/12] netvm: Prevent a stream-specific deadlock
From: Mel Gorman @ 2012-05-10 13:54 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, Linux-NFS, LKML, David Miller,
Trond Myklebust, Neil Brown, Christoph Hellwig, Peter Zijlstra,
Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336658065-24851-1-git-send-email-mgorman@suse.de>
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>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
include/net/sock.h | 7 ++++---
net/caif/caif_socket.c | 2 +-
net/core/sock.c | 2 +-
net/ipv4/tcp_input.c | 12 ++++++------
net/sctp/ulpevent.c | 2 +-
5 files changed, 13 insertions(+), 12 deletions(-)
diff --git a/include/net/sock.h b/include/net/sock.h
index 7f04aa8..3a8cce7 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1280,12 +1280,13 @@ static inline int sk_wmem_schedule(struct sock *sk, int size)
__sk_mem_schedule(sk, size, SK_MEM_SEND);
}
-static inline int sk_rmem_schedule(struct sock *sk, int size)
+static inline int sk_rmem_schedule(struct sock *sk, struct sk_buff *skb)
{
if (!sk_has_account(sk))
return 1;
- return size <= sk->sk_forward_alloc ||
- __sk_mem_schedule(sk, size, SK_MEM_RECV);
+ return skb->truesize <= sk->sk_forward_alloc ||
+ __sk_mem_schedule(sk, skb->truesize, SK_MEM_RECV) ||
+ skb_pfmemalloc(skb);
}
static inline void sk_mem_reclaim(struct sock *sk)
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 5016fa5..aaf711c 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -142,7 +142,7 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
err = sk_filter(sk, skb);
if (err)
return err;
- if (!sk_rmem_schedule(sk, skb->truesize) && rx_flow_is_on(cf_sk)) {
+ if (!sk_rmem_schedule(sk, skb) && rx_flow_is_on(cf_sk)) {
set_rx_flow_off(cf_sk);
if (net_ratelimit())
pr_debug("sending flow OFF due to rmem_schedule\n");
diff --git a/net/core/sock.c b/net/core/sock.c
index 9ad1ed9..4193266 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -391,7 +391,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
if (err)
return err;
- if (!sk_rmem_schedule(sk, skb->truesize)) {
+ if (!sk_rmem_schedule(sk, skb)) {
atomic_inc(&sk->sk_drops);
return -ENOBUFS;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3ff36406..686642c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4431,19 +4431,19 @@ static void tcp_ofo_queue(struct sock *sk)
static int tcp_prune_ofo_queue(struct sock *sk);
static int tcp_prune_queue(struct sock *sk);
-static inline int tcp_try_rmem_schedule(struct sock *sk, unsigned int size)
+static inline int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb)
{
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
- !sk_rmem_schedule(sk, size)) {
+ !sk_rmem_schedule(sk, skb)) {
if (tcp_prune_queue(sk) < 0)
return -1;
- if (!sk_rmem_schedule(sk, size)) {
+ if (!sk_rmem_schedule(sk, skb)) {
if (!tcp_prune_ofo_queue(sk))
return -1;
- if (!sk_rmem_schedule(sk, size))
+ if (!sk_rmem_schedule(sk, skb))
return -1;
}
}
@@ -4458,7 +4458,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
TCP_ECN_check_ce(tp, skb);
- if (tcp_try_rmem_schedule(sk, skb->truesize)) {
+ if (tcp_try_rmem_schedule(sk, skb)) {
/* TODO: should increment a counter */
__kfree_skb(skb);
return;
@@ -4627,7 +4627,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
if (eaten <= 0) {
queue_and_out:
if (eaten < 0 &&
- tcp_try_rmem_schedule(sk, skb->truesize))
+ tcp_try_rmem_schedule(sk, skb))
goto drop;
skb_set_owner_r(skb, sk);
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 8a84017..6c6ed2d 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -702,7 +702,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
if (rx_count >= asoc->base.sk->sk_rcvbuf) {
if ((asoc->base.sk->sk_userlocks & SOCK_RCVBUF_LOCK) ||
- (!sk_rmem_schedule(asoc->base.sk, chunk->skb->truesize)))
+ (!sk_rmem_schedule(asoc->base.sk, chunk->skb)))
goto fail;
}
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 02/12] selinux: tag avc cache alloc as non-critical
From: Mel Gorman @ 2012-05-10 13:54 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, Linux-NFS, LKML, David Miller,
Trond Myklebust, Neil Brown, Christoph Hellwig, Peter Zijlstra,
Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336658065-24851-1-git-send-email-mgorman@suse.de>
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>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
security/selinux/avc.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index 8ee42b2..75c2977 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -280,7 +280,7 @@ static struct avc_node *avc_alloc_node(void)
{
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;
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 03/12] mm: Methods for teaching filesystems about PG_swapcache pages
From: Mel Gorman @ 2012-05-10 13:54 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, Linux-NFS, LKML, David Miller,
Trond Myklebust, Neil Brown, Christoph Hellwig, Peter Zijlstra,
Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336658065-24851-1-git-send-email-mgorman@suse.de>
In order to teach filesystems to handle swap cache pages, three new
page functions are introduced:
pgoff_t page_file_index(struct page *);
loff_t page_file_offset(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_offset() - uses page_file_index(), so that it will give
the expected result, even 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.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
include/linux/mm.h | 25 +++++++++++++++++++++++++
include/linux/pagemap.h | 5 +++++
mm/swapfile.c | 19 +++++++++++++++++++
3 files changed, 49 insertions(+)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 74aa71b..58cc925 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -803,6 +803,17 @@ static inline void *page_rmapping(struct page *page)
return (void *)((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS);
}
+extern struct address_space *__page_file_mapping(struct page *);
+
+static inline
+struct address_space *page_file_mapping(struct page *page)
+{
+ if (unlikely(PageSwapCache(page)))
+ return __page_file_mapping(page);
+
+ return page->mapping;
+}
+
static inline int PageAnon(struct page *page)
{
return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
@@ -819,6 +830,20 @@ static inline pgoff_t page_index(struct page *page)
return page->index;
}
+extern pgoff_t __page_file_index(struct page *page);
+
+/*
+ * 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)
+{
+ if (unlikely(PageSwapCache(page)))
+ return __page_file_index(page);
+
+ return page->index;
+}
+
/*
* Return true if this page is mapped into pagetables.
*/
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index cfaaa69..d4d4bda 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -286,6 +286,11 @@ static inline loff_t page_offset(struct page *page)
return ((loff_t)page->index) << PAGE_CACHE_SHIFT;
}
+static inline loff_t page_file_offset(struct page *page)
+{
+ return ((loff_t)page_file_index(page)) << PAGE_CACHE_SHIFT;
+}
+
extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
unsigned long address);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index fafc26d..df5f148 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -31,6 +31,7 @@
#include <linux/memcontrol.h>
#include <linux/poll.h>
#include <linux/oom.h>
+#include <linux/export.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
@@ -2293,6 +2294,24 @@ int swapcache_prepare(swp_entry_t entry)
}
/*
+ * out-of-line __page_file_ methods to avoid include hell.
+ */
+struct address_space *__page_file_mapping(struct page *page)
+{
+ VM_BUG_ON(!PageSwapCache(page));
+ return page_swap_info(page)->swap_file->f_mapping;
+}
+EXPORT_SYMBOL_GPL(__page_file_mapping);
+
+pgoff_t __page_file_index(struct page *page)
+{
+ swp_entry_t swap = { .val = page_private(page) };
+ VM_BUG_ON(!PageSwapCache(page));
+ return swp_offset(swap);
+}
+EXPORT_SYMBOL_GPL(__page_file_index);
+
+/*
* add_swap_count_continuation - called when a swap count is duplicated
* beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's
* page of the original vmalloc'ed swap_map, to hold the continuation count
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 04/12] mm: Add support for a filesystem to activate swap files and use direct_IO for writing swap pages
From: Mel Gorman @ 2012-05-10 13:54 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, Linux-NFS, LKML, David Miller,
Trond Myklebust, Neil Brown, Christoph Hellwig, Peter Zijlstra,
Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336658065-24851-1-git-send-email-mgorman@suse.de>
Currently swapfiles are managed entirely by the core VM by using ->bmap
to allocate space and write to the blocks directly. This effectively
ensures that the underlying blocks are allocated and avoids the need
for the swap subsystem to locate what physical blocks store offsets
within a file.
If the swap subsystem is to use the filesystem information to locate
the blocks, it is critical that information such as block groups,
block bitmaps and the block descriptor table that map the swap file
were resident in memory. This patch adds address_space_operations that
the VM can call when activating or deactivating swap backed by a file.
int swap_activate(struct file *);
int swap_deactivate(struct file *);
The ->swap_activate() method is used to communicate to the
file that the VM relies on it, and the address_space should take
adequate measures such as reserving space in the underlying device,
reserving memory for mempools and pinning information such as the
block descriptor table in memory. The ->swap_deactivate() method is
called on sys_swapoff() if ->swap_activate() returned success.
After a successful swapfile ->swap_activate, the swapfile
is marked SWP_FILE and swapper_space.a_ops will proxy to
sis->swap_file->f_mappings->a_ops using ->direct_io to write swapcache
pages and ->readpage to read.
It is perfectly possible that direct_IO be used to read the swap
pages but it is an unnecessary complication. Similarly, it is possible
that ->writepage be used instead of direct_io to write the pages but
filesystem developers have stated that calling writepage from the VM
is undesirable for a variety of reasons and using direct_IO opens up
the possibility of writing back batches of swap pages in the future.
[a.p.zijlstra@chello.nl: Original patch]
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
Documentation/filesystems/Locking | 13 ++++++++++
Documentation/filesystems/vfs.txt | 12 +++++++++
include/linux/fs.h | 4 +++
include/linux/swap.h | 3 +++
mm/page_io.c | 52 +++++++++++++++++++++++++++++++++++++
mm/swap_state.c | 2 +-
mm/swapfile.c | 30 +++++++++++++++++++--
7 files changed, 113 insertions(+), 3 deletions(-)
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 4fca82e..b01c2d7 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -202,6 +202,8 @@ prototypes:
int (*launder_page)(struct page *);
int (*is_partially_uptodate)(struct page *, read_descriptor_t *, unsigned long);
int (*error_remove_page)(struct address_space *, struct page *);
+ int (*swap_activate)(struct file *);
+ int (*swap_deactivate)(struct file *);
locking rules:
All except set_page_dirty and freepage may block
@@ -225,6 +227,8 @@ migratepage: yes (both)
launder_page: yes
is_partially_uptodate: yes
error_remove_page: yes
+swap_activate: no
+swap_deactivate: no
->write_begin(), ->write_end(), ->sync_page() and ->readpage()
may be called from the request handler (/dev/loop).
@@ -326,6 +330,15 @@ cleaned, or an error value if not. Note that in order to prevent the page
getting mapped back in and redirtied, it needs to be kept locked
across the entire operation.
+ ->swap_activate will be called with a non-zero argument on
+files backing (non block device backed) swapfiles. A return value
+of zero indicates success, in which case this file can be used for
+backing swapspace. The swapspace operations will be proxied to the
+address space operations.
+
+ ->swap_deactivate() will be called in the sys_swapoff()
+path after ->swap_activate() returned success.
+
----------------------- file_lock_operations ------------------------------
prototypes:
void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 0d04920..fbd357b 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -581,6 +581,8 @@ struct address_space_operations {
int (*migratepage) (struct page *, struct page *);
int (*launder_page) (struct page *);
int (*error_remove_page) (struct mapping *mapping, struct page *page);
+ int (*swap_activate)(struct file *);
+ int (*swap_deactivate)(struct file *);
};
writepage: called by the VM to write a dirty page to backing store.
@@ -749,6 +751,16 @@ struct address_space_operations {
Setting this implies you deal with pages going away under you,
unless you have them locked or reference counts increased.
+ swap_activate: Called when swapon is used on a file to allocate
+ space if necessary and pin the block lookup information in
+ memory. A return value of zero indicates success,
+ in which case this file can be used to back swapspace. The
+ swapspace operations will be proxied to this address space's
+ ->swap_{out,in} methods.
+
+ swap_deactivate: Called during swapoff on files where swap_activate
+ was successful.
+
The File Object
===============
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8de6755..0dcd1e8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -626,6 +626,10 @@ struct address_space_operations {
int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
unsigned long);
int (*error_remove_page)(struct address_space *, struct page *);
+
+ /* swapfile support */
+ int (*swap_activate)(struct file *file);
+ int (*swap_deactivate)(struct file *file);
};
extern const struct address_space_operations empty_aops;
diff --git a/include/linux/swap.h b/include/linux/swap.h
index b1fd5c7..6b40350 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -151,6 +151,7 @@ enum {
SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */
SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */
SWP_BLKDEV = (1 << 6), /* its a block device */
+ SWP_FILE = (1 << 7), /* set after swap_activate success */
/* add others here before... */
SWP_SCANNING = (1 << 8), /* refcount in scan_swap_map */
};
@@ -316,6 +317,7 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t ent)
/* linux/mm/page_io.c */
extern int swap_readpage(struct page *);
extern int swap_writepage(struct page *page, struct writeback_control *wbc);
+extern int swap_set_page_dirty(struct page *page);
extern void end_swap_bio_read(struct bio *bio, int err);
/* linux/mm/swap_state.c */
@@ -351,6 +353,7 @@ extern int swap_type_of(dev_t, sector_t, struct block_device **);
extern unsigned int count_swap_pages(int, int);
extern sector_t map_swap_page(struct page *, struct block_device **);
extern sector_t swapdev_block(int, pgoff_t);
+extern struct swap_info_struct *page_swap_info(struct page *);
extern int reuse_swap_page(struct page *);
extern int try_to_free_swap(struct page *);
struct backing_dev_info;
diff --git a/mm/page_io.c b/mm/page_io.c
index dc76b4d..68d8357 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -17,6 +17,7 @@
#include <linux/swap.h>
#include <linux/bio.h>
#include <linux/swapops.h>
+#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <asm/pgtable.h>
@@ -93,11 +94,38 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
{
struct bio *bio;
int ret = 0, rw = WRITE;
+ struct swap_info_struct *sis = page_swap_info(page);
if (try_to_free_swap(page)) {
unlock_page(page);
goto out;
}
+
+ if (sis->flags & SWP_FILE) {
+ struct kiocb kiocb;
+ struct file *swap_file = sis->swap_file;
+ struct address_space *mapping = swap_file->f_mapping;
+ struct iovec iov = {
+ .iov_base = page_address(page),
+ .iov_len = PAGE_SIZE,
+ };
+
+ init_sync_kiocb(&kiocb, swap_file);
+ kiocb.ki_pos = page_file_offset(page);
+ kiocb.ki_left = PAGE_SIZE;
+ kiocb.ki_nbytes = PAGE_SIZE;
+
+ unlock_page(page);
+ ret = mapping->a_ops->direct_IO(KERNEL_WRITE,
+ &kiocb, &iov,
+ kiocb.ki_pos, 1);
+ if (ret == PAGE_SIZE) {
+ count_vm_event(PSWPOUT);
+ ret = 0;
+ }
+ return ret;
+ }
+
bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write);
if (bio == NULL) {
set_page_dirty(page);
@@ -119,9 +147,21 @@ int swap_readpage(struct page *page)
{
struct bio *bio;
int ret = 0;
+ struct swap_info_struct *sis = page_swap_info(page);
VM_BUG_ON(!PageLocked(page));
VM_BUG_ON(PageUptodate(page));
+
+ if (sis->flags & SWP_FILE) {
+ struct file *swap_file = sis->swap_file;
+ struct address_space *mapping = swap_file->f_mapping;
+
+ ret = mapping->a_ops->readpage(swap_file, page);
+ if (!ret)
+ count_vm_event(PSWPIN);
+ return ret;
+ }
+
bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
if (bio == NULL) {
unlock_page(page);
@@ -133,3 +173,15 @@ int swap_readpage(struct page *page)
out:
return ret;
}
+
+int swap_set_page_dirty(struct page *page)
+{
+ struct swap_info_struct *sis = page_swap_info(page);
+
+ if (sis->flags & SWP_FILE) {
+ struct address_space *mapping = sis->swap_file->f_mapping;
+ return mapping->a_ops->set_page_dirty(page);
+ } else {
+ return __set_page_dirty_no_writeback(page);
+ }
+}
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 4c5ff7f..c25b9cf 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -26,7 +26,7 @@
*/
static const struct address_space_operations swap_aops = {
.writepage = swap_writepage,
- .set_page_dirty = __set_page_dirty_no_writeback,
+ .set_page_dirty = swap_set_page_dirty,
.migratepage = migrate_page,
};
diff --git a/mm/swapfile.c b/mm/swapfile.c
index df5f148..fe2ed44 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1342,6 +1342,14 @@ static void destroy_swap_extents(struct swap_info_struct *sis)
list_del(&se->list);
kfree(se);
}
+
+ if (sis->flags & SWP_FILE) {
+ struct file *swap_file = sis->swap_file;
+ struct address_space *mapping = swap_file->f_mapping;
+
+ sis->flags &= ~SWP_FILE;
+ mapping->a_ops->swap_deactivate(swap_file);
+ }
}
/*
@@ -1423,7 +1431,9 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
*/
static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
{
- struct inode *inode;
+ struct file *swap_file = sis->swap_file;
+ struct address_space *mapping = swap_file->f_mapping;
+ struct inode *inode = mapping->host;
unsigned blocks_per_page;
unsigned long page_no;
unsigned blkbits;
@@ -1434,13 +1444,22 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
int nr_extents = 0;
int ret;
- inode = sis->swap_file->f_mapping->host;
if (S_ISBLK(inode->i_mode)) {
ret = add_swap_extent(sis, 0, sis->max, 0);
*span = sis->pages;
goto out;
}
+ if (mapping->a_ops->swap_activate) {
+ ret = mapping->a_ops->swap_activate(swap_file);
+ if (!ret) {
+ sis->flags |= SWP_FILE;
+ ret = add_swap_extent(sis, 0, sis->max, 0);
+ *span = sis->pages;
+ }
+ goto out;
+ }
+
blkbits = inode->i_blkbits;
blocks_per_page = PAGE_SIZE >> blkbits;
@@ -2293,6 +2312,13 @@ int swapcache_prepare(swp_entry_t entry)
return __swap_duplicate(entry, SWAP_HAS_CACHE);
}
+struct swap_info_struct *page_swap_info(struct page *page)
+{
+ swp_entry_t swap = { .val = page_private(page) };
+ BUG_ON(!PageSwapCache(page));
+ return swap_info[swp_type(swap)];
+}
+
/*
* out-of-line __page_file_ methods to avoid include hell.
*/
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 05/12] mm: swap: Implement generic handler for swap_activate
From: Mel Gorman @ 2012-05-10 13:54 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, Linux-NFS, LKML, David Miller,
Trond Myklebust, Neil Brown, Christoph Hellwig, Peter Zijlstra,
Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336658065-24851-1-git-send-email-mgorman@suse.de>
The version of swap_activate introduced is sufficient for swap-over-NFS
but would not provide enough information to implement a generic handler.
This patch shuffles things slightly to ensure the same information is
available for aops->swap_activate() as is available to the core.
No functionality change.
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
include/linux/fs.h | 6 ++--
include/linux/swap.h | 5 +++
mm/page_io.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++++++
mm/swapfile.c | 91 +++----------------------------------------------
4 files changed, 106 insertions(+), 88 deletions(-)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0dcd1e8..d48e8b8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -417,6 +417,7 @@ struct kstatfs;
struct vm_area_struct;
struct vfsmount;
struct cred;
+struct swap_info_struct;
extern void __init inode_init(void);
extern void __init inode_init_early(void);
@@ -628,8 +629,9 @@ struct address_space_operations {
int (*error_remove_page)(struct address_space *, struct page *);
/* swapfile support */
- int (*swap_activate)(struct file *file);
- int (*swap_deactivate)(struct file *file);
+ int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
+ sector_t *span);
+ void (*swap_deactivate)(struct file *file);
};
extern const struct address_space_operations empty_aops;
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 6b40350..4ab2276 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -320,6 +320,11 @@ extern int swap_writepage(struct page *page, struct writeback_control *wbc);
extern int swap_set_page_dirty(struct page *page);
extern void end_swap_bio_read(struct bio *bio, int err);
+int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
+ unsigned long nr_pages, sector_t start_block);
+int generic_swapfile_activate(struct swap_info_struct *, struct file *,
+ sector_t *);
+
/* linux/mm/swap_state.c */
extern struct address_space swapper_space;
#define total_swapcache_pages swapper_space.nrpages
diff --git a/mm/page_io.c b/mm/page_io.c
index 68d8357..f363261 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -86,6 +86,98 @@ void end_swap_bio_read(struct bio *bio, int err)
bio_put(bio);
}
+int generic_swapfile_activate(struct swap_info_struct *sis,
+ struct file *swap_file,
+ sector_t *span)
+{
+ struct address_space *mapping = swap_file->f_mapping;
+ struct inode *inode = mapping->host;
+ unsigned blocks_per_page;
+ unsigned long page_no;
+ unsigned blkbits;
+ sector_t probe_block;
+ sector_t last_block;
+ sector_t lowest_block = -1;
+ sector_t highest_block = 0;
+ int nr_extents = 0;
+ int ret;
+
+ blkbits = inode->i_blkbits;
+ blocks_per_page = PAGE_SIZE >> blkbits;
+
+ /*
+ * Map all the blocks into the extent list. This code doesn't try
+ * to be very smart.
+ */
+ probe_block = 0;
+ page_no = 0;
+ last_block = i_size_read(inode) >> blkbits;
+ while ((probe_block + blocks_per_page) <= last_block &&
+ page_no < sis->max) {
+ unsigned block_in_page;
+ sector_t first_block;
+
+ first_block = bmap(inode, probe_block);
+ if (first_block == 0)
+ goto bad_bmap;
+
+ /*
+ * It must be PAGE_SIZE aligned on-disk
+ */
+ if (first_block & (blocks_per_page - 1)) {
+ probe_block++;
+ goto reprobe;
+ }
+
+ for (block_in_page = 1; block_in_page < blocks_per_page;
+ block_in_page++) {
+ sector_t block;
+
+ block = bmap(inode, probe_block + block_in_page);
+ if (block == 0)
+ goto bad_bmap;
+ if (block != first_block + block_in_page) {
+ /* Discontiguity */
+ probe_block++;
+ goto reprobe;
+ }
+ }
+
+ first_block >>= (PAGE_SHIFT - blkbits);
+ if (page_no) { /* exclude the header page */
+ if (first_block < lowest_block)
+ lowest_block = first_block;
+ if (first_block > highest_block)
+ highest_block = first_block;
+ }
+
+ /*
+ * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
+ */
+ ret = add_swap_extent(sis, page_no, 1, first_block);
+ if (ret < 0)
+ goto out;
+ nr_extents += ret;
+ page_no++;
+ probe_block += blocks_per_page;
+reprobe:
+ continue;
+ }
+ ret = nr_extents;
+ *span = 1 + highest_block - lowest_block;
+ if (page_no == 0)
+ page_no = 1; /* force Empty message */
+ sis->max = page_no;
+ sis->pages = page_no - 1;
+ sis->highest_bit = page_no - 1;
+out:
+ return ret;
+bad_bmap:
+ printk(KERN_ERR "swapon: swapfile has holes\n");
+ ret = -EINVAL;
+ goto out;
+}
+
/*
* We may have stale swap cache pages in memory: notice
* them here and get rid of the unnecessary final write.
diff --git a/mm/swapfile.c b/mm/swapfile.c
index fe2ed44..80b3415 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1358,7 +1358,7 @@ static void destroy_swap_extents(struct swap_info_struct *sis)
*
* This function rather assumes that it is called in ascending page order.
*/
-static int
+int
add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
unsigned long nr_pages, sector_t start_block)
{
@@ -1434,106 +1434,25 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
struct file *swap_file = sis->swap_file;
struct address_space *mapping = swap_file->f_mapping;
struct inode *inode = mapping->host;
- unsigned blocks_per_page;
- unsigned long page_no;
- unsigned blkbits;
- sector_t probe_block;
- sector_t last_block;
- sector_t lowest_block = -1;
- sector_t highest_block = 0;
- int nr_extents = 0;
int ret;
if (S_ISBLK(inode->i_mode)) {
ret = add_swap_extent(sis, 0, sis->max, 0);
*span = sis->pages;
- goto out;
+ return ret;
}
if (mapping->a_ops->swap_activate) {
- ret = mapping->a_ops->swap_activate(swap_file);
+ ret = mapping->a_ops->swap_activate(sis, swap_file, span);
if (!ret) {
sis->flags |= SWP_FILE;
ret = add_swap_extent(sis, 0, sis->max, 0);
*span = sis->pages;
}
- goto out;
+ return ret;
}
- blkbits = inode->i_blkbits;
- blocks_per_page = PAGE_SIZE >> blkbits;
-
- /*
- * Map all the blocks into the extent list. This code doesn't try
- * to be very smart.
- */
- probe_block = 0;
- page_no = 0;
- last_block = i_size_read(inode) >> blkbits;
- while ((probe_block + blocks_per_page) <= last_block &&
- page_no < sis->max) {
- unsigned block_in_page;
- sector_t first_block;
-
- first_block = bmap(inode, probe_block);
- if (first_block == 0)
- goto bad_bmap;
-
- /*
- * It must be PAGE_SIZE aligned on-disk
- */
- if (first_block & (blocks_per_page - 1)) {
- probe_block++;
- goto reprobe;
- }
-
- for (block_in_page = 1; block_in_page < blocks_per_page;
- block_in_page++) {
- sector_t block;
-
- block = bmap(inode, probe_block + block_in_page);
- if (block == 0)
- goto bad_bmap;
- if (block != first_block + block_in_page) {
- /* Discontiguity */
- probe_block++;
- goto reprobe;
- }
- }
-
- first_block >>= (PAGE_SHIFT - blkbits);
- if (page_no) { /* exclude the header page */
- if (first_block < lowest_block)
- lowest_block = first_block;
- if (first_block > highest_block)
- highest_block = first_block;
- }
-
- /*
- * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
- */
- ret = add_swap_extent(sis, page_no, 1, first_block);
- if (ret < 0)
- goto out;
- nr_extents += ret;
- page_no++;
- probe_block += blocks_per_page;
-reprobe:
- continue;
- }
- ret = nr_extents;
- *span = 1 + highest_block - lowest_block;
- if (page_no == 0)
- page_no = 1; /* force Empty message */
- sis->max = page_no;
- sis->pages = page_no - 1;
- sis->highest_bit = page_no - 1;
-out:
- return ret;
-bad_bmap:
- printk(KERN_ERR "swapon: swapfile has holes\n");
- ret = -EINVAL;
- goto out;
+ return generic_swapfile_activate(sis, swap_file, span);
}
static void enable_swap_info(struct swap_info_struct *p, int prio,
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 06/12] mm: Add get_kernel_page[s] for pinning of kernel addresses for I/O
From: Mel Gorman @ 2012-05-10 13:54 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, Linux-NFS, LKML, David Miller,
Trond Myklebust, Neil Brown, Christoph Hellwig, Peter Zijlstra,
Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336658065-24851-1-git-send-email-mgorman@suse.de>
This patch adds two new APIs get_kernel_pages() and get_kernel_page()
that may be used to pin a vector of kernel addresses for IO. The initial
user is expected to be NFS for allowing pages to be written to swap
using aops->direct_IO(). Strictly speaking, swap-over-NFS only needs
to pin one page for IO but it makes sense to express the API in terms
of a vector and add a helper for pinning single pages.
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
include/linux/blk_types.h | 2 ++
include/linux/fs.h | 2 ++
include/linux/mm.h | 4 ++++
mm/memory.c | 53 +++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 61 insertions(+)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 4053cbd..1e62642 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -150,6 +150,7 @@ enum rq_flag_bits {
__REQ_FLUSH_SEQ, /* request for flush sequence */
__REQ_IO_STAT, /* account I/O stat */
__REQ_MIXED_MERGE, /* merge of different types, fail separately */
+ __REQ_KERNEL, /* direct IO to kernel pages */
__REQ_NR_BITS, /* stops here */
};
@@ -191,5 +192,6 @@ enum rq_flag_bits {
#define REQ_IO_STAT (1 << __REQ_IO_STAT)
#define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE)
#define REQ_SECURE (1 << __REQ_SECURE)
+#define REQ_KERNEL (1 << __REQ_KERNEL)
#endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index d48e8b8..150bc85 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -165,6 +165,8 @@ struct inodes_stat_t {
#define READ 0
#define WRITE RW_MASK
#define READA RWA_MASK
+#define KERNEL_READ (READ|REQ_KERNEL)
+#define KERNEL_WRITE (WRITE|REQ_KERNEL)
#define READ_SYNC (READ | REQ_SYNC)
#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 58cc925..cf4a730 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1023,6 +1023,10 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
struct page **pages, struct vm_area_struct **vmas);
int get_user_pages_fast(unsigned long start, int nr_pages, int write,
struct page **pages);
+struct kvec;
+int get_kernel_pages(const struct kvec *iov, int nr_pages, int write,
+ struct page **pages);
+int get_kernel_page(unsigned long start, int write, struct page **pages);
struct page *get_dump_page(unsigned long addr);
extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
diff --git a/mm/memory.c b/mm/memory.c
index 6105f47..0bc990e7 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1837,6 +1837,59 @@ next_page:
EXPORT_SYMBOL(__get_user_pages);
/*
+ * get_kernel_pages() - pin kernel pages in memory
+ * @kiov: An array of struct kvec structures
+ * @nr_segs: number of segments to pin
+ * @write: pinning for read/write, currently ignored
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_segs long.
+ *
+ * Returns number of pages pinned. This may be fewer than the number
+ * requested. If nr_pages is 0 or negative, returns 0. If no pages
+ * were pinned, returns -errno. Each page returned must be released
+ * with a put_page() call when it is finished with.
+ */
+int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write,
+ struct page **pages)
+{
+ int seg;
+
+ for (seg = 0; seg < nr_segs; seg++) {
+ if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE))
+ return seg;
+
+ /* virt_to_page sanity checks the PFN */
+ pages[seg] = virt_to_page(kiov[seg].iov_base);
+ page_cache_get(pages[seg]);
+ }
+
+ return seg;
+}
+EXPORT_SYMBOL_GPL(get_kernel_pages);
+
+/*
+ * get_kernel_page() - pin a kernel page in memory
+ * @start: starting kernel address
+ * @write: pinning for read/write, currently ignored
+ * @pages: array that receives pointer to the page pinned.
+ * Must be at least nr_segs long.
+ *
+ * Returns 1 if page is pinned. If the page was not pinned, returns
+ * -errno. The page returned must be released with a put_page() call
+ * when it is finished with.
+ */
+int get_kernel_page(unsigned long start, int write, struct page **pages)
+{
+ const struct kvec kiov = {
+ .iov_base = (void *)start,
+ .iov_len = PAGE_SIZE
+ };
+
+ return get_kernel_pages(&kiov, 1, write, pages);
+}
+EXPORT_SYMBOL_GPL(get_kernel_page);
+
+/*
* fixup_user_fault() - manually resolve a user page fault
* @tsk: the task_struct to use for page fault accounting, or
* NULL if faults are not to be recorded.
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 07/12] mm: Add support for direct_IO to highmem pages
From: Mel Gorman @ 2012-05-10 13:54 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, Linux-NFS, LKML, David Miller,
Trond Myklebust, Neil Brown, Christoph Hellwig, Peter Zijlstra,
Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336658065-24851-1-git-send-email-mgorman@suse.de>
The patch "mm: Add support for a filesystem to activate swap files and
use direct_IO for writing swap pages" added support for using direct_IO
to write swap pages but it is insufficient for highmem pages.
To support highmem pages, this patch kmaps() the page before calling the
direct_IO() handler. As direct_IO deals with virtual addresses an
additional helper is necessary for get_kernel_pages() to lookup the
struct page for a kmap virtual address.
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
include/linux/highmem.h | 7 +++++++
mm/highmem.c | 12 ++++++++++++
mm/memory.c | 3 +--
mm/page_io.c | 3 ++-
4 files changed, 22 insertions(+), 3 deletions(-)
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index d3999b4..e186e3c 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -39,10 +39,17 @@ extern unsigned long totalhigh_pages;
void kmap_flush_unused(void);
+struct page *kmap_to_page(void *addr);
+
#else /* CONFIG_HIGHMEM */
static inline unsigned int nr_free_highpages(void) { return 0; }
+static inline struct page *kmap_to_page(void *addr)
+{
+ return virt_to_page(addr);
+}
+
#define totalhigh_pages 0UL
#ifndef ARCH_HAS_KMAP
diff --git a/mm/highmem.c b/mm/highmem.c
index 57d82c6..d517cd1 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -94,6 +94,18 @@ static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait);
do { spin_unlock(&kmap_lock); (void)(flags); } while (0)
#endif
+struct page *kmap_to_page(void *vaddr)
+{
+ unsigned long addr = (unsigned long)vaddr;
+
+ if (addr >= PKMAP_ADDR(0) && addr <= PKMAP_ADDR(LAST_PKMAP)) {
+ int i = (addr - PKMAP_ADDR(0)) >> PAGE_SHIFT;
+ return pte_page(pkmap_page_table[i]);
+ }
+
+ return virt_to_page(addr);
+}
+
static void flush_all_zero_pkmaps(void)
{
int i;
diff --git a/mm/memory.c b/mm/memory.c
index 0bc990e7..fd32a1a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1858,8 +1858,7 @@ int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write,
if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE))
return seg;
- /* virt_to_page sanity checks the PFN */
- pages[seg] = virt_to_page(kiov[seg].iov_base);
+ pages[seg] = kmap_to_page(kiov[seg].iov_base);
page_cache_get(pages[seg]);
}
diff --git a/mm/page_io.c b/mm/page_io.c
index f363261..1e39e88 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -198,7 +198,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
struct file *swap_file = sis->swap_file;
struct address_space *mapping = swap_file->f_mapping;
struct iovec iov = {
- .iov_base = page_address(page),
+ .iov_base = kmap(page),
.iov_len = PAGE_SIZE,
};
@@ -211,6 +211,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
ret = mapping->a_ops->direct_IO(KERNEL_WRITE,
&kiocb, &iov,
kiocb.ki_pos, 1);
+ kunmap(page);
if (ret == PAGE_SIZE) {
count_vm_event(PSWPOUT);
ret = 0;
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 08/12] nfs: teach the NFS client how to treat PG_swapcache pages
From: Mel Gorman @ 2012-05-10 13:54 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, Linux-NFS, LKML, David Miller,
Trond Myklebust, Neil Brown, Christoph Hellwig, Peter Zijlstra,
Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336658065-24851-1-git-send-email-mgorman@suse.de>
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>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
fs/nfs/file.c | 6 +++---
fs/nfs/internal.h | 7 ++++---
fs/nfs/pagelist.c | 4 ++--
fs/nfs/read.c | 6 +++---
fs/nfs/write.c | 40 +++++++++++++++++++++-------------------
5 files changed, 33 insertions(+), 30 deletions(-)
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index aa9b709..6ead5e3 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -434,7 +434,7 @@ static void nfs_invalidate_page(struct page *page, unsigned long offset)
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);
nfs_fscache_invalidate_page(page, page->mapping->host);
}
@@ -476,7 +476,7 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
*/
static int nfs_launder_page(struct page *page)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = page_file_mapping(page)->host;
struct nfs_inode *nfsi = NFS_I(inode);
dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n",
@@ -525,7 +525,7 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
nfs_fscache_wait_on_page_write(NFS_I(dentry->d_inode), page);
lock_page(page);
- mapping = page->mapping;
+ mapping = page_file_mapping(page);
if (mapping != dentry->d_inode->i_mapping)
goto out_unlock;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 2476dc69..a7c16f3 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -434,13 +434,14 @@ void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize)
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;
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index d21fcea..77aa83e 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -77,11 +77,11 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
* 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;
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 0a4be28..fb69784 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -548,11 +548,11 @@ static const struct rpc_call_ops nfs_read_full_ops = {
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);
@@ -606,7 +606,7 @@ 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;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index c074623..8223b2c 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -125,7 +125,7 @@ static struct nfs_page *nfs_page_find_request_locked(struct page *page)
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);
@@ -137,16 +137,16 @@ static struct nfs_page *nfs_page_find_request(struct page *page)
/* 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;
pgoff_t end_index;
spin_lock(&inode->i_lock);
i_size = i_size_read(inode);
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)
goto out;
- end = ((loff_t)page->index << PAGE_CACHE_SHIFT) + ((loff_t)offset+count);
+ end = page_file_offset(page) + ((loff_t)offset+count);
if (i_size >= end)
goto out;
i_size_write(inode, end);
@@ -159,7 +159,7 @@ out:
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
@@ -200,7 +200,7 @@ static int nfs_set_page_writeback(struct page *page)
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);
page_cache_get(page);
@@ -215,7 +215,7 @@ static int nfs_set_page_writeback(struct page *page)
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);
@@ -226,7 +226,7 @@ static void nfs_end_page_writeback(struct page *page)
static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblock)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = page_file_mapping(page)->host;
struct nfs_page *req;
int ret;
@@ -287,13 +287,13 @@ out:
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;
int ret;
nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1);
- nfs_pageio_cond_complete(pgio, page->index);
+ nfs_pageio_cond_complete(pgio, page_file_index(page));
ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE);
if (ret == -EAGAIN) {
redirty_page_for_writepage(wbc, page);
@@ -310,7 +310,8 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc
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)
@@ -441,7 +442,8 @@ nfs_request_add_commit_list(struct nfs_page *req, struct list_head *head)
NFS_I(inode)->ncommit++;
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);
}
EXPORT_SYMBOL_GPL(nfs_request_add_commit_list);
@@ -486,7 +488,7 @@ static void
nfs_clear_page_commit(struct page *page)
{
dec_zone_page_state(page, NR_UNSTABLE_NFS);
- dec_bdi_stat(page->mapping->backing_dev_info, BDI_RECLAIMABLE);
+ dec_bdi_stat(page_file_mapping(page)->backing_dev_info, BDI_RECLAIMABLE);
}
static void
@@ -703,7 +705,7 @@ out_err:
static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx,
struct page *page, unsigned int offset, unsigned int bytes)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = page_file_mapping(page)->host;
struct nfs_page *req;
req = nfs_try_to_update_request(inode, page, offset, bytes);
@@ -756,7 +758,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
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;
}
@@ -782,7 +784,7 @@ int nfs_updatepage(struct file *file, struct page *page,
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);
@@ -790,7 +792,7 @@ int nfs_updatepage(struct file *file, struct page *page,
dprintk("NFS: nfs_updatepage(%s/%s %d@%lld)\n",
file->f_path.dentry->d_parent->d_name.name,
file->f_path.dentry->d_name.name, count,
- (long long)(page_offset(page) + offset));
+ (long long)(page_file_offset(page) + offset));
/* If we're not using byte range locks, and we know the page
* is up to date, it may be more efficient to extend the write
@@ -1150,7 +1152,7 @@ static void nfs_writeback_release_partial(void *calldata)
}
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)) {
@@ -1442,7 +1444,7 @@ void nfs_retry_commit(struct list_head *page_list,
nfs_list_remove_request(req);
nfs_mark_request_commit(req, lseg);
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_unlock_request(req);
}
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 09/12] nfs: disable data cache revalidation for swapfiles
From: Mel Gorman @ 2012-05-10 13:54 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, Linux-NFS, LKML, David Miller,
Trond Myklebust, Neil Brown, Christoph Hellwig, Peter Zijlstra,
Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336658065-24851-1-git-send-email-mgorman@suse.de>
The VM does not like PG_private set on PG_swapcache pages. As suggested
by Trond in http://lkml.org/lkml/2006/8/25/348, this patch disables
NFS data cache revalidation on swap files. as it does not make
sense to have other clients change the file while it is being used as
swap. This avoids setting PG_private on swap pages, since there ought
to be no further races with invalidate_inode_pages2() to deal with.
Since we cannot set PG_private we cannot use page->private which
is already used by PG_swapcache pages to store the nfs_page. Thus
augment the new nfs_page_find_request logic.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
fs/nfs/inode.c | 6 ++++++
fs/nfs/write.c | 49 +++++++++++++++++++++++++++++++++++--------------
2 files changed, 41 insertions(+), 14 deletions(-)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index e8bbfa5..af43ef6 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -880,6 +880,12 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
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_cache_expired(inode)
|| NFS_STALE(inode)) {
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 8223b2c..21cfe71 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -111,15 +111,28 @@ static void nfs_context_set_write_error(struct nfs_open_context *ctx, int 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)
{
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))) {
+ struct nfs_page *freq, *t;
+
+ /* Linearly search the commit list for the correct req */
+ list_for_each_entry_safe(freq, t, &nfsi->commit_list, wb_list) {
+ if (freq->wb_page == page) {
+ req = freq;
+ break;
+ }
+ }
}
+
+ if (req)
+ kref_get(&req->wb_kref);
+
return req;
}
@@ -129,7 +142,7 @@ static struct nfs_page *nfs_page_find_request(struct page *page)
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;
}
@@ -232,7 +245,7 @@ static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblo
spin_lock(&inode->i_lock);
for (;;) {
- req = nfs_page_find_request_locked(page);
+ req = nfs_page_find_request_locked(NFS_I(inode), page);
if (req == NULL)
break;
if (nfs_lock_request_dontget(req))
@@ -385,9 +398,15 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
spin_lock(&inode->i_lock);
if (!nfsi->npages && nfs_have_delegation(inode, FMODE_WRITE))
inode->i_version++;
- set_bit(PG_MAPPED, &req->wb_flags);
- 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))) {
+ set_bit(PG_MAPPED, &req->wb_flags);
+ SetPagePrivate(req->wb_page);
+ set_page_private(req->wb_page, (unsigned long)req);
+ }
nfsi->npages++;
kref_get(&req->wb_kref);
spin_unlock(&inode->i_lock);
@@ -404,9 +423,11 @@ static void nfs_inode_remove_request(struct nfs_page *req)
BUG_ON (!NFS_WBACK_BUSY(req));
spin_lock(&inode->i_lock);
- set_page_private(req->wb_page, 0);
- ClearPagePrivate(req->wb_page);
- clear_bit(PG_MAPPED, &req->wb_flags);
+ if (likely(!PageSwapCache(req->wb_page))) {
+ set_page_private(req->wb_page, 0);
+ ClearPagePrivate(req->wb_page);
+ clear_bit(PG_MAPPED, &req->wb_flags);
+ }
nfsi->npages--;
spin_unlock(&inode->i_lock);
nfs_release_request(req);
@@ -646,7 +667,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
spin_lock(&inode->i_lock);
for (;;) {
- req = nfs_page_find_request_locked(page);
+ req = nfs_page_find_request_locked(NFS_I(inode), page);
if (req == NULL)
goto out_unlock;
@@ -1691,7 +1712,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page)
*/
int nfs_wb_page(struct inode *inode, struct page *page)
{
- loff_t range_start = page_offset(page);
+ loff_t range_start = page_file_offset(page);
loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 10/12] nfs: enable swap on NFS
From: Mel Gorman @ 2012-05-10 13:54 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, Linux-NFS, LKML, David Miller,
Trond Myklebust, Neil Brown, Christoph Hellwig, Peter Zijlstra,
Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336658065-24851-1-git-send-email-mgorman@suse.de>
Implement the new swapfile a_ops for NFS and hook up ->direct_IO. 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.
[dfeng@redhat.com: Fix handling of multiple swap files]
[a.p.zijlstra@chello.nl: Original patch]
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
fs/nfs/Kconfig | 8 ++++
fs/nfs/direct.c | 94 +++++++++++++++++++++++++++++--------------
fs/nfs/file.c | 22 +++++++++-
include/linux/nfs_fs.h | 4 +-
include/linux/sunrpc/xprt.h | 3 ++
net/sunrpc/Kconfig | 5 +++
net/sunrpc/clnt.c | 2 +
net/sunrpc/sched.c | 7 +++-
net/sunrpc/xprtsock.c | 53 ++++++++++++++++++++++++
9 files changed, 161 insertions(+), 37 deletions(-)
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 2a0e6c5..ff93d0c 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -75,6 +75,14 @@ config NFS_V4
If unsure, say Y.
+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.
+
config NFS_V4_1
bool "NFS client support for NFSv4.1 (EXPERIMENTAL)"
depends on NFS_FS && NFS_V4 && EXPERIMENTAL
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 481be7f..2ef7395 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -111,17 +111,28 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
* @nr_segs: size of iovec array
*
* The presence of this routine in the address space ops vector means
- * the NFS client supports direct I/O. However, we shunt off direct
- * read and write requests before the VFS gets them, so this method
- * should never be called.
+ * the NFS client supports direct I/O. However, for most direct IO, we
+ * shunt off direct read and write requests before the VFS gets them,
+ * so this method is only ever called for swap.
*/
ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs)
{
+#ifndef CONFIG_NFS_SWAP
dprintk("NFS: nfs_direct_IO (%s) off/no(%Ld/%lu) EINVAL\n",
iocb->ki_filp->f_path.dentry->d_name.name,
(long long) pos, nr_segs);
return -EINVAL;
+#else
+ VM_BUG_ON(iocb->ki_left != PAGE_SIZE);
+ VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE);
+
+ if (rw == READ || rw == KERNEL_READ)
+ return nfs_file_direct_read(iocb, iov, nr_segs, pos,
+ rw == READ ? true : false);
+ return nfs_file_direct_write(iocb, iov, nr_segs, pos,
+ rw == WRITE ? true : false);
+#endif /* CONFIG_NFS_SWAP */
}
static void nfs_direct_dirty_pages(struct page **pages, unsigned int pgbase, size_t count)
@@ -278,7 +289,7 @@ static const struct rpc_call_ops nfs_read_direct_ops = {
*/
static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq,
const struct iovec *iov,
- loff_t pos)
+ loff_t pos, bool uio)
{
struct nfs_open_context *ctx = dreq->ctx;
struct inode *inode = ctx->dentry->d_inode;
@@ -312,13 +323,22 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq,
if (unlikely(!data))
break;
- down_read(¤t->mm->mmap_sem);
- result = get_user_pages(current, current->mm, user_addr,
- data->npages, 1, 0, data->pagevec, NULL);
- up_read(¤t->mm->mmap_sem);
- if (result < 0) {
- nfs_readdata_free(data);
- break;
+ if (uio) {
+ down_read(¤t->mm->mmap_sem);
+ result = get_user_pages(current, current->mm, user_addr,
+ data->npages, 1, 0, data->pagevec, NULL);
+ up_read(¤t->mm->mmap_sem);
+ if (result < 0) {
+ nfs_readdata_free(data);
+ break;
+ }
+ } else {
+ WARN_ON(data->npages != 1);
+ result = get_kernel_page(user_addr, 1, data->pagevec);
+ if (WARN_ON(result != 1)) {
+ nfs_readdata_free(data);
+ break;
+ }
}
if ((unsigned)result < data->npages) {
bytes = result * PAGE_SIZE;
@@ -386,7 +406,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq,
static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
const struct iovec *iov,
unsigned long nr_segs,
- loff_t pos)
+ loff_t pos, bool uio)
{
ssize_t result = -EINVAL;
size_t requested_bytes = 0;
@@ -396,7 +416,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
for (seg = 0; seg < nr_segs; seg++) {
const struct iovec *vec = &iov[seg];
- result = nfs_direct_read_schedule_segment(dreq, vec, pos);
+ result = nfs_direct_read_schedule_segment(dreq, vec, pos, uio);
if (result < 0)
break;
requested_bytes += result;
@@ -420,7 +440,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
}
static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ unsigned long nr_segs, loff_t pos, bool uio)
{
ssize_t result = -ENOMEM;
struct inode *inode = iocb->ki_filp->f_mapping->host;
@@ -438,7 +458,7 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
if (!is_sync_kiocb(iocb))
dreq->iocb = iocb;
- result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos);
+ result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos, uio);
if (!result)
result = nfs_direct_wait(dreq);
out_release:
@@ -705,7 +725,8 @@ static const struct rpc_call_ops nfs_write_direct_ops = {
*/
static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq,
const struct iovec *iov,
- loff_t pos, int sync)
+ loff_t pos, int sync,
+ bool uio)
{
struct nfs_open_context *ctx = dreq->ctx;
struct inode *inode = ctx->dentry->d_inode;
@@ -739,13 +760,22 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq,
if (unlikely(!data))
break;
- down_read(¤t->mm->mmap_sem);
- result = get_user_pages(current, current->mm, user_addr,
- data->npages, 0, 0, data->pagevec, NULL);
- up_read(¤t->mm->mmap_sem);
- if (result < 0) {
- nfs_writedata_free(data);
- break;
+ if (uio) {
+ down_read(¤t->mm->mmap_sem);
+ result = get_user_pages(current, current->mm, user_addr,
+ data->npages, 0, 0, data->pagevec, NULL);
+ up_read(¤t->mm->mmap_sem);
+ if (result < 0) {
+ nfs_writedata_free(data);
+ break;
+ }
+ } else {
+ WARN_ON(data->npages != 1);
+ result = get_kernel_page(user_addr, 0, data->pagevec);
+ if (WARN_ON(result != 1)) {
+ nfs_writedata_free(data);
+ break;
+ }
}
if ((unsigned)result < data->npages) {
bytes = result * PAGE_SIZE;
@@ -817,7 +847,8 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq,
static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
const struct iovec *iov,
unsigned long nr_segs,
- loff_t pos, int sync)
+ loff_t pos, int sync,
+ bool uio)
{
ssize_t result = 0;
size_t requested_bytes = 0;
@@ -828,7 +859,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
for (seg = 0; seg < nr_segs; seg++) {
const struct iovec *vec = &iov[seg];
result = nfs_direct_write_schedule_segment(dreq, vec,
- pos, sync);
+ pos, sync, uio);
if (result < 0)
break;
requested_bytes += result;
@@ -853,7 +884,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos,
- size_t count)
+ size_t count, bool uio)
{
ssize_t result = -ENOMEM;
struct inode *inode = iocb->ki_filp->f_mapping->host;
@@ -877,7 +908,8 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
if (!is_sync_kiocb(iocb))
dreq->iocb = iocb;
- result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, sync);
+ result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos,
+ sync, uio);
if (!result)
result = nfs_direct_wait(dreq);
out_release:
@@ -908,7 +940,7 @@ out:
* cache.
*/
ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ unsigned long nr_segs, loff_t pos, bool uio)
{
ssize_t retval = -EINVAL;
struct file *file = iocb->ki_filp;
@@ -933,7 +965,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
task_io_account_read(count);
- retval = nfs_direct_read(iocb, iov, nr_segs, pos);
+ retval = nfs_direct_read(iocb, iov, nr_segs, pos, uio);
if (retval > 0)
iocb->ki_pos = pos + retval;
@@ -964,7 +996,7 @@ out:
* is no atomic O_APPEND write facility in the NFS protocol.
*/
ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ unsigned long nr_segs, loff_t pos, bool uio)
{
ssize_t retval = -EINVAL;
struct file *file = iocb->ki_filp;
@@ -996,7 +1028,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
task_io_account_write(count);
- retval = nfs_direct_write(iocb, iov, nr_segs, pos, count);
+ retval = nfs_direct_write(iocb, iov, nr_segs, pos, count, uio);
if (retval > 0)
iocb->ki_pos = pos + retval;
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 6ead5e3..0e330f2 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -187,7 +187,7 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
ssize_t result;
if (iocb->ki_filp->f_flags & O_DIRECT)
- return nfs_file_direct_read(iocb, iov, nr_segs, pos);
+ return nfs_file_direct_read(iocb, iov, nr_segs, pos, true);
dprintk("NFS: read(%s/%s, %lu@%lu)\n",
dentry->d_parent->d_name.name, dentry->d_name.name,
@@ -486,6 +486,20 @@ static int nfs_launder_page(struct page *page)
return nfs_wb_page(inode, page);
}
+#ifdef CONFIG_NFS_SWAP
+static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
+ sector_t *span)
+{
+ *span = sis->pages;
+ return xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 1);
+}
+
+static void nfs_swap_deactivate(struct file *file)
+{
+ xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 0);
+}
+#endif
+
const struct address_space_operations nfs_file_aops = {
.readpage = nfs_readpage,
.readpages = nfs_readpages,
@@ -500,6 +514,10 @@ const struct address_space_operations nfs_file_aops = {
.migratepage = nfs_migrate_page,
.launder_page = nfs_launder_page,
.error_remove_page = generic_error_remove_page,
+#ifdef CONFIG_NFS_SWAP
+ .swap_activate = nfs_swap_activate,
+ .swap_deactivate = nfs_swap_deactivate,
+#endif
};
/*
@@ -574,7 +592,7 @@ static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
size_t count = iov_length(iov, nr_segs);
if (iocb->ki_filp->f_flags & O_DIRECT)
- return nfs_file_direct_write(iocb, iov, nr_segs, pos);
+ return nfs_file_direct_write(iocb, iov, nr_segs, pos, true);
dprintk("NFS: write(%s/%s, %lu@%Ld)\n",
dentry->d_parent->d_name.name, dentry->d_name.name,
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 52a1bdb..1f4efab 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -481,10 +481,10 @@ extern ssize_t nfs_direct_IO(int, struct kiocb *, const struct iovec *, loff_t,
unsigned long);
extern ssize_t nfs_file_direct_read(struct kiocb *iocb,
const struct iovec *iov, unsigned long nr_segs,
- loff_t pos);
+ loff_t pos, bool uio);
extern ssize_t nfs_file_direct_write(struct kiocb *iocb,
const struct iovec *iov, unsigned long nr_segs,
- loff_t pos);
+ loff_t pos, bool uio);
/*
* linux/fs/nfs/dir.c
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 77d278d..cff40aa 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -174,6 +174,8 @@ struct rpc_xprt {
unsigned long state; /* transport state */
unsigned char shutdown : 1, /* being shut down */
resvport : 1; /* use a reserved port */
+ unsigned int swapper; /* we're swapping over this
+ transport */
unsigned int bind_index; /* bind function index */
/*
@@ -316,6 +318,7 @@ void xprt_release_rqst_cong(struct rpc_task *task);
void xprt_disconnect_done(struct rpc_xprt *xprt);
void xprt_force_disconnect(struct rpc_xprt *xprt);
void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie);
+int xs_swapper(struct rpc_xprt *xprt, int enable);
/*
* Reserved bit positions in xprt->state
diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index 9fe8857..03d03e3 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -21,6 +21,11 @@ config SUNRPC_XPRT_RDMA
If unsure, say N.
+config SUNRPC_SWAP
+ bool
+ depends on SUNRPC
+ select NETVM
+
config RPCSEC_GSS_KRB5
tristate "Secure RPC: Kerberos V mechanism"
depends on SUNRPC && CRYPTO
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 6797246..c01d35f 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -691,6 +691,8 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt)
atomic_inc(&clnt->cl_count);
if (clnt->cl_softrtry)
task->tk_flags |= RPC_TASK_SOFT;
+ if (task->tk_client->cl_xprt->swapper)
+ task->tk_flags |= RPC_TASK_SWAPPER;
/* Add to the client's list of all tasks */
spin_lock(&clnt->cl_lock);
list_add_tail(&task->tk_task, &clnt->cl_tasks);
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 994cfea..83a4c43 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -812,7 +812,10 @@ static void rpc_async_schedule(struct work_struct *work)
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)
@@ -886,7 +889,7 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta
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);
}
/*
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 890b03f..b84df34 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1930,6 +1930,45 @@ out:
xprt_wake_pending_tasks(xprt, status);
}
+#ifdef CONFIG_SUNRPC_SWAP
+static void xs_set_memalloc(struct rpc_xprt *xprt)
+{
+ struct sock_xprt *transport = container_of(xprt, struct sock_xprt,
+ xprt);
+
+ if (xprt->swapper)
+ sk_set_memalloc(transport->inet);
+}
+
+/**
+ * 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) {
+ xprt->swapper++;
+ xs_set_memalloc(xprt);
+ } else if (xprt->swapper) {
+ xprt->swapper--;
+ sk_clear_memalloc(transport->inet);
+ }
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(xs_swapper);
+#else
+static void xs_set_memalloc(struct rpc_xprt *xprt)
+{
+}
+#endif
+
static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
{
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
@@ -1954,6 +1993,8 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
transport->sock = sock;
transport->inet = sk;
+ xs_set_memalloc(xprt);
+
write_unlock_bh(&sk->sk_callback_lock);
}
xs_udp_do_set_buffer_size(xprt);
@@ -1965,11 +2006,15 @@ static void xs_udp_setup_socket(struct work_struct *work)
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 status = -EIO;
if (xprt->shutdown)
goto out;
+ if (xprt->swapper)
+ current->flags |= PF_MEMALLOC;
+
/* Start by resetting any existing state */
xs_reset_transport(transport);
sock = xs_create_sock(xprt, transport,
@@ -1988,6 +2033,7 @@ static void xs_udp_setup_socket(struct work_struct *work)
out:
xprt_clear_connecting(xprt);
xprt_wake_pending_tasks(xprt, status);
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
}
/*
@@ -2078,6 +2124,8 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
if (!xprt_bound(xprt))
goto out;
+ xs_set_memalloc(xprt);
+
/* Tell the socket layer to start connecting... */
xprt->stat.connect_count++;
xprt->stat.connect_start = jiffies;
@@ -2108,11 +2156,15 @@ static void xs_tcp_setup_socket(struct work_struct *work)
container_of(work, struct sock_xprt, connect_worker.work);
struct socket *sock = transport->sock;
struct rpc_xprt *xprt = &transport->xprt;
+ unsigned long pflags = current->flags;
int status = -EIO;
if (xprt->shutdown)
goto out;
+ if (xprt->swapper)
+ current->flags |= PF_MEMALLOC;
+
if (!sock) {
clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
sock = xs_create_sock(xprt, transport,
@@ -2174,6 +2226,7 @@ out_eagain:
out:
xprt_clear_connecting(xprt);
xprt_wake_pending_tasks(xprt, status);
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
}
/**
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 11/12] nfs: Prevent page allocator recursions with swap over NFS.
From: Mel Gorman @ 2012-05-10 13:54 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, Linux-NFS, LKML, David Miller,
Trond Myklebust, Neil Brown, Christoph Hellwig, Peter Zijlstra,
Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336658065-24851-1-git-send-email-mgorman@suse.de>
GFP_NOFS is _more_ permissive than GFP_NOIO in that it will initiate
IO, just not of any filesystem data.
The problem is that previously NOFS was correct because that avoids
recursion into the NFS code. With swap-over-NFS, it is no longer
correct as swap IO can lead to this recursion.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
fs/nfs/pagelist.c | 2 +-
fs/nfs/write.c | 7 ++++---
2 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 77aa83e..8e80d71 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -29,7 +29,7 @@ static struct kmem_cache *nfs_page_cachep;
static inline struct nfs_page *
nfs_page_alloc(void)
{
- struct nfs_page *p = kmem_cache_zalloc(nfs_page_cachep, GFP_KERNEL);
+ struct nfs_page *p = kmem_cache_zalloc(nfs_page_cachep, GFP_NOIO);
if (p)
INIT_LIST_HEAD(&p->wb_list);
return p;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 21cfe71..abdbe61 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -52,7 +52,7 @@ static mempool_t *nfs_commit_mempool;
struct nfs_write_data *nfs_commitdata_alloc(void)
{
- struct nfs_write_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOFS);
+ struct nfs_write_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOIO);
if (p) {
memset(p, 0, sizeof(*p));
@@ -72,7 +72,7 @@ EXPORT_SYMBOL_GPL(nfs_commit_free);
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 = mempool_alloc(nfs_wdata_mempool, GFP_NOIO);
if (p) {
memset(p, 0, sizeof(*p));
@@ -81,7 +81,8 @@ struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount)
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) {
mempool_free(p, nfs_wdata_mempool);
p = NULL;
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 12/12] Avoid dereferencing bd_disk during swap_entry_free for network storage
From: Mel Gorman @ 2012-05-10 13:54 UTC (permalink / raw)
To: Andrew Morton
Cc: Linux-MM, Linux-Netdev, Linux-NFS, LKML, David Miller,
Trond Myklebust, Neil Brown, Christoph Hellwig, Peter Zijlstra,
Mike Christie, Eric B Munson, Mel Gorman
In-Reply-To: <1336658065-24851-1-git-send-email-mgorman@suse.de>
Commit [b3a27d: swap: Add swap slot free callback to
block_device_operations] dereferences p->bdev->bd_disk but this is a
NULL dereference if using swap-over-NFS. This patch checks SWP_BLKDEV
on the swap_info_struct before dereferencing.
With reference to this callback, Christoph Hellwig stated "Please
just remove the callback entirely. It has no user outside the staging
tree and was added clearly against the rules for that staging tree".
This would also be my preference but there was not an obvious way of
keeping zram in staging/ happy.
Signed-off-by: Xiaotian Feng <dfeng@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
mm/swapfile.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 80b3415..d85d842 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -547,7 +547,6 @@ static unsigned char swap_entry_free(struct swap_info_struct *p,
/* free if no reference */
if (!usage) {
- struct gendisk *disk = p->bdev->bd_disk;
if (offset < p->lowest_bit)
p->lowest_bit = offset;
if (offset > p->highest_bit)
@@ -557,9 +556,11 @@ static unsigned char swap_entry_free(struct swap_info_struct *p,
swap_list.next = p->type;
nr_swap_pages++;
p->inuse_pages--;
- if ((p->flags & SWP_BLKDEV) &&
- disk->fops->swap_slot_free_notify)
- disk->fops->swap_slot_free_notify(p->bdev, offset);
+ if (p->flags & SWP_BLKDEV) {
+ struct gendisk *disk = p->bdev->bd_disk;
+ if (disk->fops->swap_slot_free_notify)
+ disk->fops->swap_slot_free_notify(p->bdev, offset);
+ }
}
return usage;
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH] ehea: fix losing of NEQ events when one event occurred early
From: Thadeu Lima de Souza Cascardo @ 2012-05-10 14:00 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Thadeu Lima de Souza Cascardo
In-Reply-To: <20120509.202913.886545227635873372.davem@davemloft.net>
The NEQ interrupt is only triggered when there was no previous pending
interrupt. If we request irq handling after an interrupt has occurred,
we will never get an interrupt until we call H_RESET_EVENTS.
Events seem to be cleared when we first register the NEQ. So, when we
requested irq handling right after registering it, a possible race with
an interrupt was much less likely. Now, there is a chance we may lose
this race and never get any events.
The fix here is to poll and acknowledge any events that might have
happened right after registering the irq handler.
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
---
drivers/net/ethernet/ibm/ehea/ehea_main.c | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index c9069a2..f4d2da0 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -3335,6 +3335,8 @@ static int __devinit ehea_probe_adapter(struct platform_device *dev,
goto out_shutdown_ports;
}
+ /* Handle any events that might be pending. */
+ tasklet_hi_schedule(&adapter->neq_tasklet);
ret = 0;
goto out;
--
1.7.4.4
^ permalink raw reply related
* Re: [PATCH 1/2 net] 6lowpan: add missing pskb_may_pull() check
From: Alexander Smirnov @ 2012-05-10 14:05 UTC (permalink / raw)
To: Eric Dumazet; +Cc: netdev
In-Reply-To: <1336656659.12504.153.camel@edumazet-glaptop>
Hi Eric,
2012/5/10 Eric Dumazet <eric.dumazet@gmail.com>:
> On Thu, 2012-05-10 at 17:22 +0400, alex.bluesman.smirnov@gmail.com
> wrote:
>> From: Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
>>
>> Add pskb_may_pull() call when fetching u8 from skb.
>>
>> Signed-off-by: Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
>> ---
>> net/ieee802154/6lowpan.c | 2 ++
>> 1 files changed, 2 insertions(+), 0 deletions(-)
>>
>> diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c
>> index 32eb417..0ab3efe 100644
>> --- a/net/ieee802154/6lowpan.c
>> +++ b/net/ieee802154/6lowpan.c
>> @@ -295,6 +295,8 @@ static u8 lowpan_fetch_skb_u8(struct sk_buff *skb)
>> {
>> u8 ret;
>>
>> + BUG_ON(!pskb_may_pull(skb, 1));
>> +
>> ret = skb->data[0];
>> skb_pull(skb, 1);
>>
>
> No, you cant do that.
>
> pskb_may_pull() can fail, and you crash your machine instead of graceful
> error reporting.
>
thanks for the comment!
Using BUG() macro I just want to indicate that something in the bottom
of the stack went terribly wrong and you must check your code for
bugs..
>
>
^ permalink raw reply
* Re: [net-next 06/12] ixgbe: Hardware Timestamping + PTP Hardware Clock (PHC)
From: Richard Cochran @ 2012-05-10 14:11 UTC (permalink / raw)
To: Jeff Kirsher; +Cc: davem, Jacob Keller, netdev, gospo, sassmann
In-Reply-To: <1336632413-19135-7-git-send-email-jeffrey.t.kirsher@intel.com>
Mostly, this looks very good. I do have one concern and a nit, though.
On Wed, May 09, 2012 at 11:46:47PM -0700, Jeff Kirsher wrote:
> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> index 1693ec3..9a83c40 100644
> --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> @@ -789,6 +789,13 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
> total_bytes += tx_buffer->bytecount;
> total_packets += tx_buffer->gso_segs;
>
> +#ifdef CONFIG_IXGBE_PTP
> + if (unlikely(tx_buffer->tx_flags &
> + IXGBE_TX_FLAGS_TSTAMP))
> + ixgbe_ptp_tx_hwtstamp(q_vector,
> + tx_buffer->skb);
This looks strangely wrapped.
> +
> +#endif
> /* free the skb */
> dev_kfree_skb_any(tx_buffer->skb);
>
...
> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
> new file mode 100644
> index 0000000..0b6553e
> --- /dev/null
> +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
...
> +/**
> + * ixgbe_ptp_rx_hwtstamp - utility function which checks for RX time stamp
> + * @q_vector: structure containing interrupt and ring information
> + * @skb: particular skb to send timestamp with
> + *
> + * if the timestamp is valid, we convert it into the timecounter ns
> + * value, then store that result into the shhwtstamps structure which
> + * is passed up the network stack
> + */
> +void ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector,
> + struct sk_buff *skb)
> +{
> + struct ixgbe_adapter *adapter;
> + struct ixgbe_hw *hw;
> + struct skb_shared_hwtstamps *shhwtstamps;
> + u64 regval = 0, ns;
> + u32 tsyncrxctl;
> + unsigned long flags;
> +
> + /* we cannot process timestamps on a ring without a q_vector */
> + if (!q_vector || !q_vector->adapter)
> + return;
> +
> + adapter = q_vector->adapter;
> + hw = &adapter->hw;
> +
> + tsyncrxctl = IXGBE_READ_REG(hw, IXGBE_TSYNCRXCTL);
> + regval |= (u64)IXGBE_READ_REG(hw, IXGBE_RXSTMPL);
> + regval |= (u64)IXGBE_READ_REG(hw, IXGBE_RXSTMPH) << 32;
> +
> + /*
> + * If this bit is set, then the RX registers contain the time stamp. No
> + * other packet will be time stamped until we read these registers, so
> + * read the registers to make them available again. Because only one
> + * packet can be time stamped at a time, we know that the register
> + * values must belong to this one here and therefore we don't need to
> + * compare any of the additional attributes stored for it.
I suspect that this assumption is wrong. What happens if the time
stamping logic locks a value but the packet is lost because the ring
is full?
BTW, the IGB driver also has this defect.
Thanks,
Richard
^ 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