[PATCH] Replace MAX_MAP_COUNT with /proc/sys/vm/max_map_count

From: David Mosberger <davidm@napali.hpl.hp.com>

Below is a warmed up version of a patch originally done by Werner Almesberger
(see http://tinyurl.com/25zra) to replace the MAX_MAP_COUNT limit with a
sysctl variable.  I thought this had gone into the tree a long time ago but
alas it has not and as luck would have it, the hard limit bit someone today
once again with a large app on a large machine.

Here is a small test app:

Documentation/sysctl/vm.txt

@@ -22,6 +22,7 @@ Currently, these files are in /proc/sys/vm:
 - dirty_background_ratio
 - dirty_expire_centisecs
 - dirty_writeback_centisecs
+- max_map_count
 - min_free_kbytes
 
 ==============================================================
@@ -77,6 +78,21 @@ for swap because we only cluster swap data in 32-page groups.
 
 ==============================================================
 
+max_map_count:
+
+This file contains the maximum number of memory map areas a process
+may have. Memory map areas are used as a side-effect of calling
+malloc, directly by mmap and mprotect, and also when loading shared
+libraries.
+
+While most applications need less than a thousand maps, certain
+programs, particularly malloc debuggers, may consume lots of them,
+e.g., up to one or two maps per allocation.
+
+The default value is 65536.
+
+==============================================================
+
 min_free_kbytes:
 
 This is used to force the Linux VM to keep a minimum number 

include/linux/sched.h

@@ -179,7 +179,9 @@ asmlinkage void schedule(void);
 struct namespace;
 
 /* Maximum number of active map areas.. This is a random (large) number */
-#define MAX_MAP_COUNT	(65536)
+#define DEFAULT_MAX_MAP_COUNT	65536
+
+extern int sysctl_max_map_count;
 
 #include <linux/aio.h>
 

include/linux/sysctl.h

@@ -158,6 +158,7 @@ enum
 	VM_SWAPPINESS=19,	/* Tendency to steal mapped memory */
 	VM_LOWER_ZONE_PROTECTION=20,/* Amount of protection of lower zones */
 	VM_MIN_FREE_KBYTES=21,	/* Minimum free kilobytes to maintain */
+	VM_MAX_MAP_COUNT=22,	/* int: Maximum number of mmaps/address-space */
 };
 
 

kernel/sysctl.c

@@ -736,6 +736,14 @@ static ctl_table vm_table[] = {
 		.strategy	= &sysctl_intvec,
 		.extra1		= &zero,
 	},
+	{
+		.ctl_name	= VM_MAX_MAP_COUNT,
+		.procname	= "max_map_count",
+		.data		= &sysctl_max_map_count,
+		.maxlen		= sizeof(sysctl_max_map_count),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
 	{ .ctl_name = 0 }
 };
 

mm/mmap.c

@@ -54,10 +54,12 @@ pgprot_t protection_map[16] = {
 
 int sysctl_overcommit_memory = 0;	/* default is heuristic overcommit */
 int sysctl_overcommit_ratio = 50;	/* default is 50% */
+int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
 atomic_t vm_committed_space = ATOMIC_INIT(0);
 
 EXPORT_SYMBOL(sysctl_overcommit_memory);
 EXPORT_SYMBOL(sysctl_overcommit_ratio);
+EXPORT_SYMBOL(sysctl_max_map_count);
 EXPORT_SYMBOL(vm_committed_space);
 
 /*
@@ -516,7 +518,7 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
 		return -EINVAL;
 
 	/* Too many mappings? */
-	if (mm->map_count > MAX_MAP_COUNT)
+	if (mm->map_count > sysctl_max_map_count)
 		return -ENOMEM;
 
 	/* Obtain the address to map to. we verify (or select) it and ensure
@@ -1203,7 +1205,7 @@ int split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 	struct vm_area_struct *new;
 	struct address_space *mapping = NULL;
 
-	if (mm->map_count >= MAX_MAP_COUNT)
+	if (mm->map_count >= sysctl_max_map_count)
 		return -ENOMEM;
 
 	new = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
@@ -1381,7 +1383,7 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
 	    > current->rlim[RLIMIT_AS].rlim_cur)
 		return -ENOMEM;
 
-	if (mm->map_count > MAX_MAP_COUNT)
+	if (mm->map_count > sysctl_max_map_count)
 		return -ENOMEM;
 
 	if (security_vm_enough_memory(len >> PAGE_SHIFT))