fs, file table: reinit files_stat.max_files after deferred memory initialisation

Dave Hansen reported the following;

	My laptop has been behaving strangely with 4.2-rc2.  Once I log
	in to my X session, I start getting all kinds of strange errors
	from applications and see this in my dmesg:

        	VFS: file-max limit 8192 reached

The problem is that the file-max is calculated before memory is fully
initialised and miscalculates how much memory the kernel is using.  This
patch recalculates file-max after deferred memory initialisation.  Note
that using memory hotplug infrastructure would not have avoided this
problem as the value is not recalculated after memory hot-add.

4.1:             files_stat.max_files = 6582781
4.2-rc2:         files_stat.max_files = 8192
4.2-rc2 patched: files_stat.max_files = 6562467

Small differences with the patch applied and 4.1 but not enough to matter.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Dave Hansen <dave.hansen@intel.com>
Cc: Nicolai Stange <nicstange@gmail.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Alex Ng <alexng@microsoft.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/dcache.c b/fs/dcache.c
index 5c8ea15e73a53b6b6dbe3e9660973d2eda9c7800..9b5fe503f6cb6c8d76044bb8272084fdb0474c9b 100644 (file)
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -3442,22 +3442,15 @@ void __init vfs_caches_init_early(void)
        inode_init_early();
 }
 
-void __init vfs_caches_init(unsigned long mempages)
+void __init vfs_caches_init(void)
 {
-       unsigned long reserve;
-
-       /* Base hash sizes on available memory, with a reserve equal to
-           150% of current kernel size */
-
-       reserve = min((mempages - nr_free_pages()) * 3/2, mempages - 1);
-       mempages -= reserve;
-
        names_cachep = kmem_cache_create("names_cache", PATH_MAX, 0,
                        SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
 
        dcache_init();
        inode_init();
-       files_init(mempages);
+       files_init();
+       files_maxfiles_init();
        mnt_init();
        bdev_cache_init();
        chrdev_init();

diff --git a/fs/file_table.c b/fs/file_table.c
index 7f9d407c759596f950335bd418ab0226f4a629f8..ad17e05ebf95f07888b15f2b09a7b37ac89b9710 100644 (file)
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -25,6 +25,7 @@
 #include <linux/hardirq.h>
 #include <linux/task_work.h>
 #include <linux/ima.h>
+#include <linux/swap.h>
 
 #include <linux/atomic.h>
 
@@ -308,19 +309,24 @@ void put_filp(struct file *file)
        }
 }
 
-void __init files_init(unsigned long mempages)
+void __init files_init(void)
 { 
-       unsigned long n;
-
        filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
                        SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+       percpu_counter_init(&nr_files, 0, GFP_KERNEL);
+}
 
-       /*
-        * One file with associated inode and dcache is very roughly 1K.
-        * Per default don't use more than 10% of our memory for files. 
-        */ 
+/*
+ * One file with associated inode and dcache is very roughly 1K. Per default
+ * do not use more than 10% of our memory for files.
+ */
+void __init files_maxfiles_init(void)
+{
+       unsigned long n;
+       unsigned long memreserve = (totalram_pages - nr_free_pages()) * 3/2;
+
+       memreserve = min(memreserve, totalram_pages - 1);
+       n = ((totalram_pages - memreserve) * (PAGE_SIZE / 1024)) / 10;
 
-       n = (mempages * (PAGE_SIZE / 1024)) / 10;
        files_stat.max_files = max_t(unsigned long, n, NR_FILE);
-       percpu_counter_init(&nr_files, 0, GFP_KERNEL);
 } 

diff --git a/include/linux/fs.h b/include/linux/fs.h
index cc008c338f5a9bcb66076da96e929d6104697373..84b783f277f761a0ef7b940bd1fbab37db60567e 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -55,7 +55,8 @@ struct vm_fault;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
-extern void __init files_init(unsigned long);
+extern void __init files_init(void);
+extern void __init files_maxfiles_init(void);
 
 extern struct files_stat_struct files_stat;
 extern unsigned long get_max_files(void);
@@ -2245,7 +2246,7 @@ extern int ioctl_preallocate(struct file *filp, void __user *argp);
 
 /* fs/dcache.c */
 extern void __init vfs_caches_init_early(void);
-extern void __init vfs_caches_init(unsigned long);
+extern void __init vfs_caches_init(void);
 
 extern struct kmem_cache *names_cachep;
 

diff --git a/init/main.c b/init/main.c
index c5d5626289cee3a46f7e1b7d2441ca0496ba4471..56506553d4d80dff814b75f45db6db280fd0dea7 100644 (file)
--- a/init/main.c
+++ b/init/main.c
@@ -656,7 +656,7 @@ asmlinkage __visible void __init start_kernel(void)
        key_init();
        security_init();
        dbg_late_init();
-       vfs_caches_init(totalram_pages);
+       vfs_caches_init();
        signals_init();
        /* rootfs populating might need page-writeback */
        page_writeback_init();

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 322628278ae4081e3ee9cb2521f8c5392c584bda..cb61f44eb3fc4420406d72a04ad168b55524c47f 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1201,6 +1201,9 @@ void __init page_alloc_init_late(void)
 
        /* Block until all are initialised */
        wait_for_completion(&pgdat_init_all_done_comp);
+
+       /* Reinit limits that are based on free pages after the kernel is up */
+       files_maxfiles_init();
 }
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */