The patch titled
Subject: fs, file table: reinit files_stat.max_files after deferred memory initialisation
has been added to the -mm tree. Its filename is
fs-file-table-reinit-files_statmax_files-after-deferred-memory-initialisation.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/fs-file-table-reinit-files_statmax_files-after-deferred-memory-initialisation.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/fs-file-table-reinit-files_statmax_files-after-deferred-memory-initialisation.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Mel Gorman <mgorman@xxxxxxx>
Subject: 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@xxxxxxx>
Reported-by: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Nicolai Stange <nicstange@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Alex Ng <alexng@xxxxxxxxxxxxx>
Cc: Fengguang Wu <fengguang.wu@xxxxxxxxx>
Cc: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/dcache.c | 13 +++----------
fs/file_table.c | 24 +++++++++++++++---------
include/linux/fs.h | 5 +++--
init/main.c | 2 +-
mm/page_alloc.c | 3 +++
5 files changed, 25 insertions(+), 22 deletions(-)
diff -puN fs/dcache.c~fs-file-table-reinit-files_statmax_files-after-deferred-memory-initialisation fs/dcache.c
--- a/fs/dcache.c~fs-file-table-reinit-files_statmax_files-after-deferred-memory-initialisation
+++ a/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 -puN fs/file_table.c~fs-file-table-reinit-files_statmax_files-after-deferred-memory-initialisation fs/file_table.c
--- a/fs/file_table.c~fs-file-table-reinit-files_statmax_files-after-deferred-memory-initialisation
+++ a/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 -puN include/linux/fs.h~fs-file-table-reinit-files_statmax_files-after-deferred-memory-initialisation include/linux/fs.h
--- a/include/linux/fs.h~fs-file-table-reinit-files_statmax_files-after-deferred-memory-initialisation
+++ a/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
/* 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 -puN init/main.c~fs-file-table-reinit-files_statmax_files-after-deferred-memory-initialisation init/main.c
--- a/init/main.c~fs-file-table-reinit-files_statmax_files-after-deferred-memory-initialisation
+++ a/init/main.c
@@ -656,7 +656,7 @@ asmlinkage __visible void __init start_k
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 -puN mm/page_alloc.c~fs-file-table-reinit-files_statmax_files-after-deferred-memory-initialisation mm/page_alloc.c
--- a/mm/page_alloc.c~fs-file-table-reinit-files_statmax_files-after-deferred-memory-initialisation
+++ a/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 */
_
Patches currently in -mm which might be from mgorman@xxxxxxx are
mm-meminit-suppress-unused-memory-variable-warning.patch
mm-page_owner-fix-possible-access-violation.patch
mm-page_owner-set-correct-gfp_mask-on-page_owner.patch
mm-meminit-allow-early_pfn_to_nid-to-be-used-during-runtime.patch
mm-meminit-replace-rwsem-with-completion.patch
fs-file-table-reinit-files_statmax_files-after-deferred-memory-initialisation.patch
userfaultfd-linux-documentation-vm-userfaultfdtxt.patch
userfaultfd-waitqueue-add-nr-wake-parameter-to-__wake_up_locked_key.patch
userfaultfd-uapi.patch
userfaultfd-linux-userfaultfd_kh.patch
userfaultfd-add-vm_userfaultfd_ctx-to-the-vm_area_struct.patch
userfaultfd-add-vm_uffd_missing-and-vm_uffd_wp.patch
userfaultfd-call-handle_userfault-for-userfaultfd_missing-faults.patch
userfaultfd-teach-vma_merge-to-merge-across-vma-vm_userfaultfd_ctx.patch
userfaultfd-prevent-khugepaged-to-merge-if-userfaultfd-is-armed.patch
userfaultfd-add-new-syscall-to-provide-memory-externalization.patch
userfaultfd-rename-uffd_apibits-into-features.patch
userfaultfd-rename-uffd_apibits-into-features-fixup.patch
userfaultfd-change-the-read-api-to-return-a-uffd_msg.patch
userfaultfd-wake-pending-userfaults.patch
userfaultfd-optimize-read-and-poll-to-be-o1.patch
userfaultfd-allocate-the-userfaultfd_ctx-cacheline-aligned.patch
userfaultfd-solve-the-race-between-uffdio_copyzeropage-and-read.patch
userfaultfd-buildsystem-activation.patch
userfaultfd-activate-syscall.patch
userfaultfd-uffdio_copyuffdio_zeropage-uapi.patch
userfaultfd-mcopy_atomicmfill_zeropage-uffdio_copyuffdio_zeropage-preparation.patch
userfaultfd-avoid-mmap_sem-read-recursion-in-mcopy_atomic.patch
userfaultfd-uffdio_copy-and-uffdio_zeropage.patch
x86-mm-trace-when-an-ipi-is-about-to-be-sent.patch
mm-send-one-ipi-per-cpu-to-tlb-flush-all-entries-after-unmapping-pages.patch
mm-send-one-ipi-per-cpu-to-tlb-flush-all-entries-after-unmapping-pages-fix.patch
mm-defer-flush-of-writable-tlb-entries.patch
documentation-features-vm-add-feature-description-and-arch-support-status-for-batched-tlb-flush-after-unmap.patch
page-flags-trivial-cleanup-for-pagetrans-helpers.patch
page-flags-introduce-page-flags-policies-wrt-compound-pages.patch
page-flags-define-pg_locked-behavior-on-compound-pages.patch
page-flags-define-behavior-of-fs-io-related-flags-on-compound-pages.patch
page-flags-define-behavior-of-lru-related-flags-on-compound-pages.patch
page-flags-define-behavior-slb-related-flags-on-compound-pages.patch
page-flags-define-behavior-of-xen-related-flags-on-compound-pages.patch
page-flags-define-pg_reserved-behavior-on-compound-pages.patch
page-flags-define-pg_swapbacked-behavior-on-compound-pages.patch
page-flags-define-pg_swapcache-behavior-on-compound-pages.patch
page-flags-define-pg_mlocked-behavior-on-compound-pages.patch
page-flags-define-pg_uncached-behavior-on-compound-pages.patch
page-flags-define-pg_uptodate-behavior-on-compound-pages.patch
page-flags-look-on-head-page-if-the-flag-is-encoded-in-page-mapping.patch
mm-sanitize-page-mapping-for-tail-pages.patch
mm-increase-swap_cluster_max-to-batch-tlb-flushes.patch
mm-vmscan-fix-the-page-state-calculation-in-too_many_isolated.patch
mm-move-lazy-free-pages-to-inactive-list.patch
mm-move-lazy-free-pages-to-inactive-list-fix.patch
mm-move-lazy-free-pages-to-inactive-list-fix-fix.patch
linux-next.patch
do_shared_fault-check-that-mmap_sem-is-held.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
