From cfc0c4d831b7292fcb33538d7e8dff24264f7556 Mon Sep 17 00:00:00 2001
From: Kefeng Wang <wangkefeng.wang@huawei.com>
Date: Tue, 16 May 2023 14:38:20 +0800
Subject: [PATCH] mm: page_alloc: move sysctls into it own fils
References: bsc#1212886 (MM functional and performance backports)
Git-commit: e95d372c4cd46b6ec4eeacc07adcb7260ab4cfa0
Patch-mainline: v6.5-rc1
This moves all page alloc related sysctls to its own file, as part of the
kernel/sysctl.c spring cleaning, also move some functions declarations
from mm.h into internal.h.
Link: https://lkml.kernel.org/r/20230516063821.121844-13-wangkefeng.wang@huawei.com
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Len Brown <len.brown@intel.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Rafael J. Wysocki <rafael@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
include/linux/mm.h | 11 ------
include/linux/mmzone.h | 21 ----------
kernel/sysctl.c | 67 --------------------------------
mm/internal.h | 11 ++++++
mm/mm_init.c | 2 +
mm/page_alloc.c | 103 ++++++++++++++++++++++++++++++++++++++++++-------
6 files changed, 102 insertions(+), 113 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 750e1041d549..37b291b29f02 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3016,12 +3016,6 @@ extern int __meminit early_pfn_to_nid(unsigned long pfn);
#endif
extern void set_dma_reserve(unsigned long new_dma_reserve);
-extern void memmap_init_range(unsigned long, int, unsigned long,
- unsigned long, unsigned long, enum meminit_context,
- struct vmem_altmap *, int migratetype);
-extern void setup_per_zone_wmarks(void);
-extern void calculate_min_free_kbytes(void);
-extern int __meminit init_per_zone_wmark_min(void);
extern void mem_init(void);
extern void __init mmap_init(void);
@@ -3042,11 +3036,6 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...);
extern void setup_per_cpu_pageset(void);
-/* page_alloc.c */
-extern int min_free_kbytes;
-extern int watermark_boost_factor;
-extern int watermark_scale_factor;
-
/* nommu.c */
extern atomic_long_t mmap_pages_allocated;
extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 21b7fce38a1e..0ccd196d3579 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1513,27 +1513,6 @@ static inline bool has_managed_dma(void)
}
#endif
-/* These two functions are used to setup the per zone pages min values */
-struct ctl_table;
-
-int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void *, size_t *,
- loff_t *);
-int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void *,
- size_t *, loff_t *);
-extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES];
-int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void *,
- size_t *, loff_t *);
-int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *, int,
- void *, size_t *, loff_t *);
-int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int,
- void *, size_t *, loff_t *);
-int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
- void *, size_t *, loff_t *);
-int numa_zonelist_order_handler(struct ctl_table *, int,
- void *, size_t *, loff_t *);
-extern int percpu_pagelist_high_fraction;
-extern char numa_zonelist_order[];
-#define NUMA_ZONELIST_ORDER_LEN 16
#ifndef CONFIG_NUMA
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 9ca582a2c692..04859af7d295 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2128,13 +2128,6 @@ static struct ctl_table vm_table[] = {
.extra2 = SYSCTL_ONE,
},
#endif
- {
- .procname = "lowmem_reserve_ratio",
- .data = &sysctl_lowmem_reserve_ratio,
- .maxlen = sizeof(sysctl_lowmem_reserve_ratio),
- .mode = 0644,
- .proc_handler = lowmem_reserve_ratio_sysctl_handler,
- },
{
.procname = "drop_caches",
.data = &sysctl_drop_caches,
@@ -2144,39 +2137,6 @@ static struct ctl_table vm_table[] = {
.extra1 = SYSCTL_ONE,
.extra2 = SYSCTL_FOUR,
},
- {
- .procname = "min_free_kbytes",
- .data = &min_free_kbytes,
- .maxlen = sizeof(min_free_kbytes),
- .mode = 0644,
- .proc_handler = min_free_kbytes_sysctl_handler,
- .extra1 = SYSCTL_ZERO,
- },
- {
- .procname = "watermark_boost_factor",
- .data = &watermark_boost_factor,
- .maxlen = sizeof(watermark_boost_factor),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = SYSCTL_ZERO,
- },
- {
- .procname = "watermark_scale_factor",
- .data = &watermark_scale_factor,
- .maxlen = sizeof(watermark_scale_factor),
- .mode = 0644,
- .proc_handler = watermark_scale_factor_sysctl_handler,
- .extra1 = SYSCTL_ONE,
- .extra2 = SYSCTL_THREE_THOUSAND,
- },
- {
- .procname = "percpu_pagelist_high_fraction",
- .data = &percpu_pagelist_high_fraction,
- .maxlen = sizeof(percpu_pagelist_high_fraction),
- .mode = 0644,
- .proc_handler = percpu_pagelist_high_fraction_sysctl_handler,
- .extra1 = SYSCTL_ZERO,
- },
{
.procname = "page_lock_unfairness",
.data = &sysctl_page_lock_unfairness,
@@ -2232,24 +2192,6 @@ static struct ctl_table vm_table[] = {
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
},
- {
- .procname = "min_unmapped_ratio",
- .data = &sysctl_min_unmapped_ratio,
- .maxlen = sizeof(sysctl_min_unmapped_ratio),
- .mode = 0644,
- .proc_handler = sysctl_min_unmapped_ratio_sysctl_handler,
- .extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_ONE_HUNDRED,
- },
- {
- .procname = "min_slab_ratio",
- .data = &sysctl_min_slab_ratio,
- .maxlen = sizeof(sysctl_min_slab_ratio),
- .mode = 0644,
- .proc_handler = sysctl_min_slab_ratio_sysctl_handler,
- .extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_ONE_HUNDRED,
- },
#endif
#ifdef CONFIG_SMP
{
@@ -2276,15 +2218,6 @@ static struct ctl_table vm_table[] = {
.proc_handler = mmap_min_addr_handler,
},
#endif
-#ifdef CONFIG_NUMA
- {
- .procname = "numa_zonelist_order",
- .data = &numa_zonelist_order,
- .maxlen = NUMA_ZONELIST_ORDER_LEN,
- .mode = 0644,
- .proc_handler = numa_zonelist_order_handler,
- },
-#endif
#if (defined(CONFIG_X86_32) && !defined(CONFIG_UML))|| \
(defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL))
{
diff --git a/mm/internal.h b/mm/internal.h
index ebe8613bf256..df8049650957 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -207,6 +207,13 @@ static inline bool is_check_pages_enabled(void)
return static_branch_unlikely(&check_pages_enabled);
}
+extern int min_free_kbytes;
+
+void setup_per_zone_wmarks(void);
+void calculate_min_free_kbytes(void);
+int __meminit init_per_zone_wmark_min(void);
+void page_alloc_sysctl_init(void);
+
/*
* Structure for holding the mostly immutable allocation parameters passed
* between functions involved in allocations, including the alloc_pages*
@@ -417,6 +424,10 @@ extern void *memmap_alloc(phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr,
int nid, bool exact_nid);
+void memmap_init_range(unsigned long, int, unsigned long, unsigned long,
+ unsigned long, enum meminit_context, struct vmem_altmap *, int);
+
+
int split_free_page(struct page *free_page,
unsigned int order, unsigned long split_pfn_offset);
diff --git a/mm/mm_init.c b/mm/mm_init.c
index afc700cf4b4d..e3c8357a4036 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -2393,6 +2393,8 @@ void __init page_alloc_init_late(void)
/* Initialize page ext after all struct pages are initialized. */
if (deferred_struct_pages)
page_ext_init();
+
+ page_alloc_sysctl_init();
}
#ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 874e3ac39606..ebc7bda5614d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -206,7 +206,6 @@ nodemask_t node_states[NR_NODE_STATES] __read_mostly = {
};
EXPORT_SYMBOL(node_states);
-int percpu_pagelist_high_fraction;
gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
/*
@@ -302,8 +301,8 @@ compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS] = {
int min_free_kbytes = 1024;
int user_min_free_kbytes = -1;
-int watermark_boost_factor __read_mostly = 15000;
-int watermark_scale_factor = 10;
+static int watermark_boost_factor __read_mostly = 15000;
+static int watermark_scale_factor = 10;
/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
int movable_zone;
@@ -4881,12 +4880,12 @@ static int __parse_numa_zonelist_order(char *s)
return 0;
}
-char numa_zonelist_order[] = "Node";
-
+static char numa_zonelist_order[] = "Node";
+#define NUMA_ZONELIST_ORDER_LEN 16
/*
* sysctl handler for numa_zonelist_order
*/
-int numa_zonelist_order_handler(struct ctl_table *table, int write,
+static int numa_zonelist_order_handler(struct ctl_table *table, int write,
void *buffer, size_t *length, loff_t *ppos)
{
if (write)
@@ -4894,7 +4893,6 @@ int numa_zonelist_order_handler(struct ctl_table *table, int write,
return proc_dostring(table, write, buffer, length, ppos);
}
-
static int node_load[MAX_NUMNODES];
/**
@@ -5322,6 +5320,7 @@ static int zone_batchsize(struct zone *zone)
#endif
}
+static int percpu_pagelist_high_fraction;
static int zone_highsize(struct zone *zone, int batch, int cpu_online)
{
#ifdef CONFIG_MMU
@@ -5851,7 +5850,7 @@ postcore_initcall(init_per_zone_wmark_min)
* that we can call two helper functions whenever min_free_kbytes
* changes.
*/
-int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
+static int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
void *buffer, size_t *length, loff_t *ppos)
{
int rc;
@@ -5867,7 +5866,7 @@ int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
return 0;
}
-int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write,
+static int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write,
void *buffer, size_t *length, loff_t *ppos)
{
int rc;
@@ -5897,7 +5896,7 @@ static void setup_min_unmapped_ratio(void)
}
-int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
+static int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
void *buffer, size_t *length, loff_t *ppos)
{
int rc;
@@ -5924,7 +5923,7 @@ static void setup_min_slab_ratio(void)
sysctl_min_slab_ratio) / 100;
}
-int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
+static int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
void *buffer, size_t *length, loff_t *ppos)
{
int rc;
@@ -5948,8 +5947,8 @@ int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
* minimum watermarks. The lowmem reserve ratio can only make sense
* if in function of the boot time zone sizes.
*/
-int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write,
- void *buffer, size_t *length, loff_t *ppos)
+static int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table,
+ int write, void *buffer, size_t *length, loff_t *ppos)
{
int i;
@@ -5969,7 +5968,7 @@ int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write,
* cpu. It is the fraction of total pages in each zone that a hot per cpu
* pagelist can have before it gets flushed back to buddy allocator.
*/
-int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *table,
+static int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *table,
int write, void *buffer, size_t *length, loff_t *ppos)
{
struct zone *zone;
@@ -6002,6 +6001,82 @@ int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *table,
return ret;
}
+static struct ctl_table page_alloc_sysctl_table[] = {
+ {
+ .procname = "min_free_kbytes",
+ .data = &min_free_kbytes,
+ .maxlen = sizeof(min_free_kbytes),
+ .mode = 0644,
+ .proc_handler = min_free_kbytes_sysctl_handler,
+ .extra1 = SYSCTL_ZERO,
+ },
+ {
+ .procname = "watermark_boost_factor",
+ .data = &watermark_boost_factor,
+ .maxlen = sizeof(watermark_boost_factor),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ },
+ {
+ .procname = "watermark_scale_factor",
+ .data = &watermark_scale_factor,
+ .maxlen = sizeof(watermark_scale_factor),
+ .mode = 0644,
+ .proc_handler = watermark_scale_factor_sysctl_handler,
+ .extra1 = SYSCTL_ONE,
+ .extra2 = SYSCTL_THREE_THOUSAND,
+ },
+ {
+ .procname = "percpu_pagelist_high_fraction",
+ .data = &percpu_pagelist_high_fraction,
+ .maxlen = sizeof(percpu_pagelist_high_fraction),
+ .mode = 0644,
+ .proc_handler = percpu_pagelist_high_fraction_sysctl_handler,
+ .extra1 = SYSCTL_ZERO,
+ },
+ {
+ .procname = "lowmem_reserve_ratio",
+ .data = &sysctl_lowmem_reserve_ratio,
+ .maxlen = sizeof(sysctl_lowmem_reserve_ratio),
+ .mode = 0644,
+ .proc_handler = lowmem_reserve_ratio_sysctl_handler,
+ },
+#ifdef CONFIG_NUMA
+ {
+ .procname = "numa_zonelist_order",
+ .data = &numa_zonelist_order,
+ .maxlen = NUMA_ZONELIST_ORDER_LEN,
+ .mode = 0644,
+ .proc_handler = numa_zonelist_order_handler,
+ },
+ {
+ .procname = "min_unmapped_ratio",
+ .data = &sysctl_min_unmapped_ratio,
+ .maxlen = sizeof(sysctl_min_unmapped_ratio),
+ .mode = 0644,
+ .proc_handler = sysctl_min_unmapped_ratio_sysctl_handler,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE_HUNDRED,
+ },
+ {
+ .procname = "min_slab_ratio",
+ .data = &sysctl_min_slab_ratio,
+ .maxlen = sizeof(sysctl_min_slab_ratio),
+ .mode = 0644,
+ .proc_handler = sysctl_min_slab_ratio_sysctl_handler,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE_HUNDRED,
+ },
+#endif
+ {}
+};
+
+void __init page_alloc_sysctl_init(void)
+{
+ register_sysctl_init("vm", page_alloc_sysctl_table);
+}
+
#ifdef CONFIG_CONTIG_ALLOC
/* Usage: See admin-guide/dynamic-debug-howto.rst */
static void alloc_contig_dump_pages(struct list_head *page_list)