mm: add overcommit_kbytes sysctl variable

Some applications that run on HPC clusters are designed around the
availability of RAM and the overcommit ratio is fine tuned to get the
maximum usage of memory without swapping. With growing memory, the
1%-of-all-RAM grain provided by overcommit_ratio has become too coarse
for these workload (on a 2TB machine it represents no less than 20GB).

This patch adds the new overcommit_kbytes sysctl variable that allow a
much finer grain.

[[e-mail]: coding-style fixes]
[[e-mail]: fix nommu build]
Signed-off-by: Jerome Marchand <[e-mail]>
Cc: Dave Hansen <[e-mail]>
Cc: Alan Cox <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

Documentation/sysctl/vm.txt

···
 - numa_zonelist_order
 - oom_dump_tasks
 - oom_kill_allocating_task
+- overcommit_kbytes
 - overcommit_memory
 - overcommit_ratio
 - page-cluster
···
 is used in oom_kill_allocating_task.
 
 The default value is 0.
+
+==============================================================
+
+overcommit_kbytes:
+
+When overcommit_memory is set to 2, the committed address space is not
+permitted to exceed swap plus this amount of physical RAM. See below.
+
+Note: overcommit_kbytes is the counterpart of overcommit_ratio. Only one
+of them may be specified at a time. Setting one disables the other (which
+then appears as 0 when read).
 
 ==============================================================
 

Documentation/vm/overcommit-accounting

···
 
 2	-	Don't overcommit. The total address space commit
 		for the system is not permitted to exceed swap + a
-		configurable percentage (default is 50) of physical RAM.
-		Depending on the percentage you use, in most situations
+		configurable amount (default is 50%) of physical RAM.
+		Depending on the amount you use, in most situations
 		this means a process will not be killed while accessing
 		pages but will receive errors on memory allocation as
 		appropriate.
···
 
 The overcommit policy is set via the sysctl `vm.overcommit_memory'.
 
-The overcommit percentage is set via `vm.overcommit_ratio'.
+The overcommit amount can be set via `vm.overcommit_ratio' (percentage)
+or `vm.overcommit_kbytes' (absolute value).
 
 The current overcommit limit and amount committed are viewable in
 /proc/meminfo as CommitLimit and Committed_AS respectively.

include/linux/mm.h

···
 extern unsigned long sysctl_user_reserve_kbytes;
 extern unsigned long sysctl_admin_reserve_kbytes;
 
+extern int sysctl_overcommit_memory;
+extern int sysctl_overcommit_ratio;
+extern unsigned long sysctl_overcommit_kbytes;
+
+extern int overcommit_ratio_handler(struct ctl_table *, int, void __user *,
+				    size_t *, loff_t *);
+extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *,
+				    size_t *, loff_t *);
+
 #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
 
 /* to align the pointer to the (next) page boundary */

include/linux/mman.h

···
 
 extern int sysctl_overcommit_memory;
 extern int sysctl_overcommit_ratio;
+extern unsigned long sysctl_overcommit_kbytes;
 extern struct percpu_counter vm_committed_as;
 
 #ifdef CONFIG_SMP

kernel/sysctl.c

···
 #if defined(CONFIG_SYSCTL)
 
 /* External variables not in a header file. */
-extern int sysctl_overcommit_memory;
-extern int sysctl_overcommit_ratio;
 extern int max_threads;
 extern int suid_dumpable;
 #ifdef CONFIG_COREDUMP
···
 		.data		= &sysctl_overcommit_ratio,
 		.maxlen		= sizeof(sysctl_overcommit_ratio),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= overcommit_ratio_handler,
+	},
+	{
+		.procname	= "overcommit_kbytes",
+		.data		= &sysctl_overcommit_kbytes,
+		.maxlen		= sizeof(sysctl_overcommit_kbytes),
+		.mode		= 0644,
+		.proc_handler	= overcommit_kbytes_handler,
 	},
 	{
 		.procname	= "page-cluster", 

mm/mmap.c

···
 
 int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;  /* heuristic overcommit */
 int sysctl_overcommit_ratio __read_mostly = 50;	/* default is 50% */
+unsigned long sysctl_overcommit_kbytes __read_mostly;
 int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
 unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */
 unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */

mm/nommu.c

···
 struct percpu_counter vm_committed_as;
 int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
 int sysctl_overcommit_ratio = 50; /* default is 50% */
+unsigned long sysctl_overcommit_kbytes __read_mostly;
 int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
 int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
 unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */

mm/util.c

···
 	return mapping;
 }
 
+int overcommit_ratio_handler(struct ctl_table *table, int write,
+			     void __user *buffer, size_t *lenp,
+			     loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (ret == 0 && write)
+		sysctl_overcommit_kbytes = 0;
+	return ret;
+}
+
+int overcommit_kbytes_handler(struct ctl_table *table, int write,
+			     void __user *buffer, size_t *lenp,
+			     loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
+	if (ret == 0 && write)
+		sysctl_overcommit_ratio = 0;
+	return ret;
+}
+
 /*
  * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
  */
 unsigned long vm_commit_limit(void)
 {
-	return ((totalram_pages - hugetlb_total_pages())
-		* sysctl_overcommit_ratio / 100) + total_swap_pages;
+	unsigned long allowed;
+
+	if (sysctl_overcommit_kbytes)
+		allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10);
+	else
+		allowed = ((totalram_pages - hugetlb_total_pages())
+			   * sysctl_overcommit_ratio / 100);
+	allowed += total_swap_pages;
+
+	return allowed;
 }