The patch titled
Subject: mm, pcp: allow restoring percpu_pagelist_fraction default
has been removed from the -mm tree. Its filename was
mm-pcp-allow-restoring-percpu_pagelist_fraction-default.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: David Rientjes <rientjes@xxxxxxxxxx>
Subject: mm, pcp: allow restoring percpu_pagelist_fraction default
Oleg reports a division by zero error on zero-length write() to the
percpu_pagelist_fraction sysctl:
divide error: 0000 [#1] SMP DEBUG_PAGEALLOC
CPU: 1 PID: 9142 Comm: badarea_io Not tainted 3.15.0-rc2-vm-nfs+ #19
Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
task: ffff8800d5aeb6e0 ti: ffff8800d87a2000 task.ti: ffff8800d87a2000
RIP: 0010:[<ffffffff81152664>] [<ffffffff81152664>] percpu_pagelist_fraction_sysctl_handler+0x84/0x120
RSP: 0018:ffff8800d87a3e78 EFLAGS: 00010246
RAX: 0000000000000f89 RBX: ffff88011f7fd000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000010
RBP: ffff8800d87a3e98 R08: ffffffff81d002c8 R09: ffff8800d87a3f50
R10: 000000000000000b R11: 0000000000000246 R12: 0000000000000060
R13: ffffffff81c3c3e0 R14: ffffffff81cfddf8 R15: ffff8801193b0800
FS: 00007f614f1e9740(0000) GS:ffff88011f440000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 00007f614f1fa000 CR3: 00000000d9291000 CR4: 00000000000006e0
Stack:
0000000000000001 ffffffffffffffea ffffffff81c3c3e0 0000000000000000
ffff8800d87a3ee8 ffffffff8122b163 ffff8800d87a3f50 00007fff1564969c
0000000000000000 ffff8800d8098f00 00007fff1564969c ffff8800d87a3f50
Call Trace:
[<ffffffff8122b163>] proc_sys_call_handler+0xb3/0xc0
[<ffffffff8122b184>] proc_sys_write+0x14/0x20
[<ffffffff811ba93a>] vfs_write+0xba/0x1e0
[<ffffffff811bb486>] SyS_write+0x46/0xb0
[<ffffffff816db7ff>] tracesys+0xe1/0xe6
However, if the percpu_pagelist_fraction sysctl is set by the user, it is
also impossible to restore it to the kernel default since the user cannot
write 0 to the sysctl.
This patch allows the user to write 0 to restore the default behavior. It
still requires a fraction equal to or larger than 8, however, as stated by
the documentation for sanity. If a value in the range [1, 7] is written,
the sysctl will return EINVAL.
This successfully solves the divide by zero issue at the same time.
Signed-off-by: David Rientjes <rientjes@xxxxxxxxxx>
Reported-by: Oleg Drokin <green@xxxxxxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
Documentation/sysctl/vm.txt | 3 +-
kernel/sysctl.c | 3 --
mm/page_alloc.c | 40 +++++++++++++++++++++++-----------
3 files changed, 31 insertions(+), 15 deletions(-)
diff -puN Documentation/sysctl/vm.txt~mm-pcp-allow-restoring-percpu_pagelist_fraction-default Documentation/sysctl/vm.txt
--- a/Documentation/sysctl/vm.txt~mm-pcp-allow-restoring-percpu_pagelist_fraction-default
+++ a/Documentation/sysctl/vm.txt
@@ -702,7 +702,8 @@ The batch value of each per cpu pagelist
set to pcp->high/4. The upper limit of batch is (PAGE_SHIFT * 8)
The initial value is zero. Kernel does not use this value at boot time to set
-the high water marks for each per cpu page list.
+the high water marks for each per cpu page list. If the user writes '0' to this
+sysctl, it will revert to this default behavior.
==============================================================
diff -puN kernel/sysctl.c~mm-pcp-allow-restoring-percpu_pagelist_fraction-default kernel/sysctl.c
--- a/kernel/sysctl.c~mm-pcp-allow-restoring-percpu_pagelist_fraction-default
+++ a/kernel/sysctl.c
@@ -136,7 +136,6 @@ static unsigned long dirty_bytes_min = 2
/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
static int maxolduid = 65535;
static int minolduid;
-static int min_percpu_pagelist_fract = 8;
static int ngroups_max = NGROUPS_MAX;
static const int cap_last_cap = CAP_LAST_CAP;
@@ -1317,7 +1316,7 @@ static struct ctl_table vm_table[] = {
.maxlen = sizeof(percpu_pagelist_fraction),
.mode = 0644,
.proc_handler = percpu_pagelist_fraction_sysctl_handler,
- .extra1 = &min_percpu_pagelist_fract,
+ .extra1 = &zero,
},
#ifdef CONFIG_MMU
{
diff -puN mm/page_alloc.c~mm-pcp-allow-restoring-percpu_pagelist_fraction-default mm/page_alloc.c
--- a/mm/page_alloc.c~mm-pcp-allow-restoring-percpu_pagelist_fraction-default
+++ a/mm/page_alloc.c
@@ -69,6 +69,7 @@
/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
static DEFINE_MUTEX(pcp_batch_high_lock);
+#define MIN_PERCPU_PAGELIST_FRACTION (8)
#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
DEFINE_PER_CPU(int, numa_node);
@@ -4145,7 +4146,7 @@ static void __meminit zone_init_free_lis
memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY)
#endif
-static int __meminit zone_batchsize(struct zone *zone)
+static int zone_batchsize(struct zone *zone)
{
#ifdef CONFIG_MMU
int batch;
@@ -4261,8 +4262,8 @@ static void pageset_set_high(struct per_
pageset_update(&p->pcp, high, batch);
}
-static void __meminit pageset_set_high_and_batch(struct zone *zone,
- struct per_cpu_pageset *pcp)
+static void pageset_set_high_and_batch(struct zone *zone,
+ struct per_cpu_pageset *pcp)
{
if (percpu_pagelist_fraction)
pageset_set_high(pcp,
@@ -5881,23 +5882,38 @@ int percpu_pagelist_fraction_sysctl_hand
void __user *buffer, size_t *length, loff_t *ppos)
{
struct zone *zone;
- unsigned int cpu;
+ int old_percpu_pagelist_fraction;
int ret;
+ mutex_lock(&pcp_batch_high_lock);
+ old_percpu_pagelist_fraction = percpu_pagelist_fraction;
+
ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
- if (!write || (ret < 0))
- return ret;
+ if (!write || ret < 0)
+ goto out;
+
+ /* Sanity checking to avoid pcp imbalance */
+ if (percpu_pagelist_fraction &&
+ percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) {
+ percpu_pagelist_fraction = old_percpu_pagelist_fraction;
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* No change? */
+ if (percpu_pagelist_fraction == old_percpu_pagelist_fraction)
+ goto out;
- mutex_lock(&pcp_batch_high_lock);
for_each_populated_zone(zone) {
- unsigned long high;
- high = zone->managed_pages / percpu_pagelist_fraction;
+ unsigned int cpu;
+
for_each_possible_cpu(cpu)
- pageset_set_high(per_cpu_ptr(zone->pageset, cpu),
- high);
+ pageset_set_high_and_batch(zone,
+ per_cpu_ptr(zone->pageset, cpu));
}
+out:
mutex_unlock(&pcp_batch_high_lock);
- return 0;
+ return ret;
}
int hashdist = HASHDIST_DEFAULT;
_
Patches currently in -mm which might be from rientjes@xxxxxxxxxx are
origin.patch
mm-slabc-add-__init-to-init_lock_keys.patch
slab-common-add-functions-for-kmem_cache_node-access.patch
slub-use-new-node-functions.patch
slub-use-new-node-functions-fix.patch
slab-use-get_node-and-kmem_cache_node-functions.patch
slab-use-get_node-and-kmem_cache_node-functions-fix.patch
slab-use-get_node-and-kmem_cache_node-functions-fix-2.patch
mm-slabh-wrap-the-whole-file-with-guarding-macro.patch
mm-slub-mark-resiliency_test-as-init-text.patch
mm-slub-slub_debug=n-use-the-same-alloc-free-hooks-as-for-slub_debug=y.patch
mm-readaheadc-remove-unused-file_ra_state-from-count_history_pages.patch
mm-memory_hotplugc-add-__meminit-to-grow_zone_span-grow_pgdat_span.patch
mm-page_allocc-unexport-alloc_pages_exact_nid.patch
mm-page_alloc-simplify-drain_zone_pages-by-using-min.patch
memcg-cleanup-memcg_cache_params-refcnt-usage.patch
memcg-destroy-kmem-caches-when-last-slab-is-freed.patch
memcg-mark-caches-that-belong-to-offline-memcgs-as-dead.patch
slub-dont-fail-kmem_cache_shrink-if-slab-placement-optimization-fails.patch
slub-make-slab_free-non-preemptable.patch
memcg-wait-for-kfrees-to-finish-before-destroying-cache.patch
slub-make-dead-memcg-caches-discard-free-slabs-immediately.patch
slab-do-not-keep-free-objects-slabs-on-dead-memcg-caches.patch
mm-mem-hotplug-replace-simple_strtoull-with-kstrtoull.patch
include-kernelh-rewrite-min3-max3-and-clamp-using-min-and-max.patch
mm-utilc-add-kstrimdup.patch
lib-add-size-unit-t-p-e-to-memparse.patch
fs-proc-kcorec-use-page_align-instead-of-alignpage_size.patch
proc-stat-convert-to-single_open_size.patch
fs-seq_file-fallback-to-vmalloc-allocation.patch
fork-exec-cleanup-mm-initialization.patch
fork-reset-mm-pinned_vm.patch
fork-copy-mms-vm-usage-counters-under-mmap_sem.patch
linux-next.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html