Re: [PATCH v2] mm: add a low limit to alloc_large_system_hash
From: Tim Bird
Date: Wed May 23 2012 - 19:32:52 EST
This patch seems to have fallen in the cracks:
https://lkml.org/lkml/2012/2/27/20
The last message on the thread was an ACK by David Miller, and
the question "Who wants to take this?"
-- Tim
[message and patch follow]
UDP stack needs a minimum hash size value for proper operation and also
uses alloc_large_system_hash() for proper NUMA distribution of its hash
tables and automatic sizing depending on available system memory.
On some low memory situations, udp_table_init() must ignore the
alloc_large_system_hash() result and reallocs a bigger memory area.
As we cannot easily free old hash table, we leak it and kmemleak can
issue a warning.
This patch adds a low limit parameter to alloc_large_system_hash() to
solve this problem.
We then specify UDP_HTABLE_SIZE_MIN for UDP/UDPLite hash table
allocation.
Reported-by: Mark Asselstine <mark.asselstine@xxxxxxxxxxxxx>
Reported-by: Tim Bird <tim.bird@xxxxxxxxxxx>
Signed-off-by: Eric Dumazet <eric.dumazet@xxxxxxxxx>
Cc: Paul Gortmaker <paul.gortmaker@xxxxxxxxxxxxx>
---
V2: no 16 minimum value for pid hash
fs/dcache.c | 2 ++
fs/inode.c | 2 ++
include/linux/bootmem.h | 3 ++-
kernel/pid.c | 3 ++-
mm/page_alloc.c | 7 +++++--
net/ipv4/route.c | 1 +
net/ipv4/tcp.c | 2 ++
net/ipv4/udp.c | 30 ++++++++++--------------------
8 files changed, 26 insertions(+), 24 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index fe19ac1..ef5e72e 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2984,6 +2984,7 @@ static void __init dcache_init_early(void)
HASH_EARLY,
&d_hash_shift,
&d_hash_mask,
+ 0,
0);
for (loop = 0; loop < (1U << d_hash_shift); loop++)
@@ -3014,6 +3015,7 @@ static void __init dcache_init(void)
0,
&d_hash_shift,
&d_hash_mask,
+ 0,
0);
for (loop = 0; loop < (1U << d_hash_shift); loop++)
diff --git a/fs/inode.c b/fs/inode.c
index d3ebdbe..7acee4c 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1667,6 +1667,7 @@ void __init inode_init_early(void)
HASH_EARLY,
&i_hash_shift,
&i_hash_mask,
+ 0,
0);
for (loop = 0; loop < (1U << i_hash_shift); loop++)
@@ -1697,6 +1698,7 @@ void __init inode_init(void)
0,
&i_hash_shift,
&i_hash_mask,
+ 0,
0);
for (loop = 0; loop < (1U << i_hash_shift); loop++)
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 66d3e95..1a0cd27 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -154,7 +154,8 @@ extern void *alloc_large_system_hash(const char *tablename,
int flags,
unsigned int *_hash_shift,
unsigned int *_hash_mask,
- unsigned long limit);
+ unsigned long low_limit,
+ unsigned long high_limit);
#define HASH_EARLY 0x00000001 /* Allocating during early boot? */
#define HASH_SMALL 0x00000002 /* sub-page allocation allowed, min
diff --git a/kernel/pid.c b/kernel/pid.c
index 9f08dfa..e86b291 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -547,7 +547,8 @@ void __init pidhash_init(void)
pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
HASH_EARLY | HASH_SMALL,
- &pidhash_shift, NULL, 4096);
+ &pidhash_shift, NULL,
+ 0, 4096);
pidhash_size = 1U << pidhash_shift;
for (i = 0; i < pidhash_size; i++)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a13ded1..b9afccb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5198,9 +5198,10 @@ void *__init alloc_large_system_hash(const char *tablename,
int flags,
unsigned int *_hash_shift,
unsigned int *_hash_mask,
- unsigned long limit)
+ unsigned long low_limit,
+ unsigned long high_limit)
{
- unsigned long long max = limit;
+ unsigned long long max = high_limit;
unsigned long log2qty, size;
void *table = NULL;
@@ -5238,6 +5239,8 @@ void *__init alloc_large_system_hash(const char *tablename,
}
max = min(max, 0x80000000ULL);
+ if (numentries < low_limit)
+ numentries = low_limit;
if (numentries > max)
numentries = max;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index bcacf54..0a41e38 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3475,6 +3475,7 @@ int __init ip_rt_init(void)
0,
&rt_hash_log,
&rt_hash_mask,
+ 0,
rhash_entries ? 0 : 512 * 1024);
memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket));
rt_hash_lock_init();
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 22ef5f9..e61a498 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3267,6 +3267,7 @@ void __init tcp_init(void)
0,
NULL,
&tcp_hashinfo.ehash_mask,
+ 0,
thash_entries ? 0 : 512 * 1024);
for (i = 0; i <= tcp_hashinfo.ehash_mask; i++) {
INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i);
@@ -3283,6 +3284,7 @@ void __init tcp_init(void)
0,
&tcp_hashinfo.bhash_size,
NULL,
+ 0,
64 * 1024);
tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size;
for (i = 0; i < tcp_hashinfo.bhash_size; i++) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5d075b5..dc68ed2 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2182,26 +2182,16 @@ void __init udp_table_init(struct udp_table *table, const char *name)
{
unsigned int i;
- if (!CONFIG_BASE_SMALL)
- table->hash = alloc_large_system_hash(name,
- 2 * sizeof(struct udp_hslot),
- uhash_entries,
- 21, /* one slot per 2 MB */
- 0,
- &table->log,
- &table->mask,
- 64 * 1024);
- /*
- * Make sure hash table has the minimum size
- */
- if (CONFIG_BASE_SMALL || table->mask < UDP_HTABLE_SIZE_MIN - 1) {
- table->hash = kmalloc(UDP_HTABLE_SIZE_MIN *
- 2 * sizeof(struct udp_hslot), GFP_KERNEL);
- if (!table->hash)
- panic(name);
- table->log = ilog2(UDP_HTABLE_SIZE_MIN);
- table->mask = UDP_HTABLE_SIZE_MIN - 1;
- }
+ table->hash = alloc_large_system_hash(name,
+ 2 * sizeof(struct udp_hslot),
+ uhash_entries,
+ 21, /* one slot per 2 MB */
+ 0,
+ &table->log,
+ &table->mask,
+ UDP_HTABLE_SIZE_MIN,
+ 64 * 1024);
+
table->hash2 = table->hash + (table->mask + 1);
for (i = 0; i <= table->mask; i++) {
INIT_HLIST_NULLS_HEAD(&table->hash[i].head, i);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/