recalculate min_free_kbytes post memory hotplug

v2 -> v3
--------
[v2 1/2]
- removed symptoms references from changelog

[v2 2/2]
- addressed following issues Michal Hocko raised:
. nr_free_buffer_pages can oveflow in int on very large machines . min_free_kbytes can decrease the size theoretically

v1 -> v2
--------
- addressed issue Kirill A. Shutemov raised:
. changes would override min_free_kbytes set by user

Vijay Balakrishna (2):
mm: khugepaged: recalculate min_free_kbytes after memory hotplug as
expected by khugepaged
mm: khugepaged: avoid overriding min_free_kbytes set by user

 include/linux/khugepaged.h |  5 +++++
 mm/khugepaged.c            | 16 +++++++++++++---
 mm/memory_hotplug.c        |  3 +++
 mm/page_alloc.c            |  2 +-
 4 files changed, 22 insertions(+), 4 deletions(-)

2.28.0

When memory is hotplug added or removed the min_free_kbytes must be recalculated based on what is expected by khugepaged. Currently after hotplug, min_free_kbytes will be set to a lower default and higher default set when THP enabled is lost. This change restores min_free_kbytes as expected for THP consumers.

---
 include/linux/khugepaged.h |  5 +++++
 mm/khugepaged.c            | 13 +++++++++++--
 mm/memory_hotplug.c        |  3 +++
 3 files changed, 19 insertions(+), 2 deletions(-)

index bc45ea1efbf7..c941b7377321 100644
@@ -15,6 +15,7 @@ extern int __khugepaged_enter(struct mm_struct *mm);
 extern void __khugepaged_exit(struct mm_struct *mm);
 extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
 				      unsigned long vm_flags);
+extern void khugepaged_min_free_kbytes_update(void);
 #ifdef CONFIG_SHMEM
 extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr);
 #else

@@ -85,6 +86,10 @@ static inline void collapse_pte_mapped_thp(struct mm_struct *mm,
 					   unsigned long addr)
 {
 }
+
+static inline void khugepaged_min_free_kbytes_update(void)
+{
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #endif /* _LINUX_KHUGEPAGED_H */

index cfa0dba5fd3b..4f7107476a6f 100644
@@ -56,6 +56,9 @@ enum scan_result {
 #define CREATE_TRACE_POINTS
 #include <trace/events/huge_memory.h>
 
+static struct task_struct *khugepaged_thread __read_mostly;
+static DEFINE_MUTEX(khugepaged_mutex);
+
 /* default scan 8*512 pte (or vmas) every 30 second */
 static unsigned int khugepaged_pages_to_scan __read_mostly;
 static unsigned int khugepaged_pages_collapsed;

@@ -2292,8 +2295,6 @@ static void set_recommended_min_free_kbytes(void)
 
 int start_stop_khugepaged(void)
 {
-	static struct task_struct *khugepaged_thread __read_mostly;
-	static DEFINE_MUTEX(khugepaged_mutex);
 	int err = 0;
 
 	mutex_lock(&khugepaged_mutex);

@@ -2320,3 +2321,11 @@ int start_stop_khugepaged(void)
 	mutex_unlock(&khugepaged_mutex);
 	return err;
 }
+
+void khugepaged_min_free_kbytes_update(void)
+{
+	mutex_lock(&khugepaged_mutex);
+	if (khugepaged_enabled() && khugepaged_thread)
+		set_recommended_min_free_kbytes();
+	mutex_unlock(&khugepaged_mutex);
+}

index e9d5ab5d3ca0..3e19272c1fad 100644
@@ -36,6 +36,7 @@
 #include <linux/memblock.h>
 #include <linux/compaction.h>
 #include <linux/rmap.h>
+#include <linux/khugepaged.h>
 
 #include <asm/tlbflush.h>
 

@@ -857,6 +858,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 	zone_pcp_update(zone);
 
 	init_per_zone_wmark_min();
+	khugepaged_min_free_kbytes_update();
 
 	kswapd_run(nid);
 	kcompactd_run(nid);

@@ -1600,6 +1602,7 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	pgdat_resize_unlock(zone->zone_pgdat, &flags);
 
 	init_per_zone_wmark_min();
+	khugepaged_min_free_kbytes_update();
 
 	if (!populated_zone(zone)) {
 		zone_pcp_reset(zone);

2.28.0

Hi

[This is an automated email]

This commit has been processed because it contains a "Fixes:" tag fixing commit: f000565adb77 ("thp: set recommended min free kbytes").

The bot has tested the following trees: v5.8.10, v5.4.66, v4.19.146, v4.14.198, v4.9.236, v4.4.236.

v5.8.10: Build OK!
v5.4.66: Build OK!
v4.19.146: Failed to apply! Possible dependencies:
013de2d6671d ("csky: MMU and page table management")
27e1f8273113 ("khugepaged: enable collapse pmd for pte-mapped THP") 426dcd4b600f ("hexagon: switch to NO_BOOTMEM")
6471f52af786 ("alpha: switch to NO_BOOTMEM")
9143a9359d05 ("csky: Kernel booting")
aca52c398389 ("mm: remove CONFIG_HAVE_MEMBLOCK")
bc3ec75de545 ("dma-mapping: merge direct and noncoherent ops") c32e64e852f3 ("csky: Build infrastructure")
ca9a46f8a4f0 ("mm/memory_hotplug: online_pages cannot be 0 in online_pages()") de1193f0be66 ("mm, memory_hotplug: update pcp lists everytime onlining a memory block") e0a9317d9004 ("hexagon: use generic dma_noncoherent_ops")
e900a918b098 ("mm: shuffle initial free memory to improve memory-side-cache utilization") f3ecc0ff0457 ("dma-mapping: move the dma_coherent flag to struct device") f406f222d4b2 ("hexagon: implement the sync_sg_for_device DMA operation")

v4.14.198: Failed to apply! Possible dependencies:
008ef0969dd9 ("btrfs: drop lock parameter from update_ioctl_balance_args and rename") 17ef445f9bef ("Documentation/filesystems: update documentation of file_operations") 27e1f8273113 ("khugepaged: enable collapse pmd for pte-mapped THP") 3d8f7615319b ("vfs: implement readahead(2) using POSIX_FADV_WILLNEED") 45cd0faae371 ("vfs: add the fadvise() file operation")
5740c99e9d30 ("vfs: dedupe: return int")
6e8b704df584 ("fs: update documentation to mention __poll_t and match the code") 87eb5eb24232 ("vfs: dedupe: rationalize args")
b4e98d9ac775 ("mm: account pud page tables")
c4812909f5d5 ("mm: introduce wrappers to access mm->nr_ptes")
ca9a46f8a4f0 ("mm/memory_hotplug: online_pages cannot be 0 in online_pages()") de1193f0be66 ("mm, memory_hotplug: update pcp lists everytime onlining a memory block") e900a918b098 ("mm: shuffle initial free memory to improve memory-side-cache utilization") f51d2b59120f ("btrfs: allow to set compression level for zlib") f5c29bd9dbd3 ("Btrfs: add __init macro to btrfs init functions")

v4.9.236: Failed to apply! Possible dependencies:

    0b89ede62963 ("s390/mm: fork vs. 5 level page tabel")
    27e1f8273113 ("khugepaged: enable collapse pmd for pte-mapped THP")
    505a60e22560 ("asm-generic: introduce 5level-fixup.h")
    a00cc7d9dd93 ("mm, x86: add support for PUD-sized transparent hugepages")
    b4e98d9ac775 ("mm: account pud page tables")
    c2febafc6773 ("mm: convert generic code to 5-level paging")
    c4812909f5d5 ("mm: introduce wrappers to access mm->nr_ptes")
    c763ea2650df ("x86/kconfig: Sort the 'config X86' selects alphabetically")
    d94e068573f2 ("x86/kconfig: Move 64-bit only arch Kconfig selects to 'config X86_64'")

v4.4.236: Failed to apply! Possible dependencies:
0b57d6ba0bd1 ("mm/mmap.c: remove redundant local variables for may_expand_vm()") 1170532bb49f ("mm: convert printk(KERN_<LEVEL> to pr_<level>") 27e1f8273113 ("khugepaged: enable collapse pmd for pte-mapped THP") 5a6e75f8110c ("shmem: prepare huge= mount option and sysfs knob") 756a025f0009 ("mm: coalesce split strings")
84638335900f ("mm: rework virtual memory accounting")
8cee852ec53f ("mm, procfs: breakdown RSS for anon, shmem and file in /proc/pid/status") b46e756f5e47 ("thp: extract khugepaged from mm/huge_memory.c") d07e22597d1d ("mm: mmap: add new /proc tunable for mmap_base ASLR") d977d56ce5b3 ("mm: warn about VmData over RLIMIT_DATA")
d9fe4fab1197 ("x86/mm/pat: Add untrack_pfn_moved for mremap") eca56ff906bd ("mm, shmem: add internal shmem resident memory accounting")

NOTE: The patch will not be queued to stable trees until it is upstream.

How should we proceed with this patch?

Thanks
Sasha

Can this patch be included? As Kirill is ok with patch now.

Thanks,
Vijay

He is? I can't immediately find that email.

Do we have an acked-by?

http://lkml.kernel.org/r/[email protected]

Michal Hocko
SUSE Labs

I am ok with this patch. I am not sure this is worth backporting to stable trees becasuse this is not a functional bug. Surprising behavior, yes, but not much more than that.

One minor comment below
[...]

Michal Hocko
SUSE Labs

Thanks Michal.

Sure, let me take a look and post v4 next week.

Thanks,
Vijay

set_recommended_min_free_kbytes need to honor min_free_kbytes set by the user. Post start-of-day THP enable or memory hotplug operations can lose user specified min_free_kbytes, in particular when it is higher than calculated recommended value. user_min_free_kbytes initialized to 0 to avoid undesired result when comparing with "unsigned long" type.

---
 mm/khugepaged.c | 3 ++-
 mm/page_alloc.c | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

index 4f7107476a6f..3c1147816d12 100644
@@ -2283,7 +2283,8 @@ static void set_recommended_min_free_kbytes(void)
 			      (unsigned long) nr_free_buffer_pages() / 20);
 	recommended_min <<= (PAGE_SHIFT-10);
 
-	if (recommended_min > min_free_kbytes) {
+	if (recommended_min > min_free_kbytes ||
+		recommended_min > user_min_free_kbytes) {
 		if (user_min_free_kbytes >= 0)
 			pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n",
 				min_free_kbytes, recommended_min);

index fab5e97dc9ca..7b81fb139034 100644
@@ -315,7 +315,7 @@ compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS] = {
 };
 
 int min_free_kbytes = 1024;
-int user_min_free_kbytes = -1;
+int user_min_free_kbytes = 0;
 #ifdef CONFIG_DISCONTIGMEM
 /*
  * DiscontigMem defines memory ranges as separate pg_data_t even if the ranges

2.28.0

Please ignore this patch. I forgot to run scripts/checkpatch.pl and see

CHECK: Alignment should match open parenthesis
#30: FILE: mm/khugepaged.c:2287:
+ if (recommended_min > min_free_kbytes ||
+ recommended_min > user_min_free_kbytes) {

ERROR: do not initialise globals to 0
#43: FILE: mm/page_alloc.c:318:
+int user_min_free_kbytes = 0;

Sorry for trouble, I will send a new version.

Vijay

Hi

[This is an automated email]

This commit has been processed because it contains a -stable tag. The stable tag indicates that it's relevant for the following trees: all

The bot has tested the following trees: v5.8.10, v5.4.66, v4.19.146, v4.14.198, v4.9.236, v4.4.236.

v5.8.10: Build OK!
v5.4.66: Build OK!
v4.19.146: Failed to apply! Possible dependencies:

    1c30844d2dfe ("mm: reclaim small amounts of memory when an external fragmentation event occurs")
    24512228b7a3 ("mm: do not boost watermarks to avoid fragmentation for the DISCONTIG memory model")
    426dcd4b600f ("hexagon: switch to NO_BOOTMEM")
    6471f52af786 ("alpha: switch to NO_BOOTMEM")
    6bb154504f8b ("mm, page_alloc: spread allocations across zones before introducing fragmentation")
    9705bea5f833 ("mm: convert zone->managed_pages to atomic variable")
    a921444382b4 ("mm: move zone watermark accesses behind an accessor")
    b4a991ec584b ("mm: remove CONFIG_NO_BOOTMEM")
    bc3ec75de545 ("dma-mapping: merge direct and noncoherent ops")
    bda49a81164a ("mm: remove nobootmem")
    c32e64e852f3 ("csky: Build infrastructure")
    e0a9317d9004 ("hexagon: use generic dma_noncoherent_ops")
    f406f222d4b2 ("hexagon: implement the sync_sg_for_device DMA operation")

v4.14.198: Failed to apply! Possible dependencies:
1c30844d2dfe ("mm: reclaim small amounts of memory when an external fragmentation event occurs") 1d47a3ec09b5 ("mm/cma: remove ALLOC_CMA")
24512228b7a3 ("mm: do not boost watermarks to avoid fragmentation for the DISCONTIG memory model") 3d2054ad8c2d ("ARM: CMA: avoid double mapping to the CMA area if CONFIG_HIGHMEM=y") 453f85d43fa9 ("mm: remove __GFP_COLD")
6bb154504f8b ("mm, page_alloc: spread allocations across zones before introducing fragmentation") 85ccc8fa81af ("mm/page_alloc: make sure __rmqueue() etc are always inline") a921444382b4 ("mm: move zone watermark accesses behind an accessor")
bad8c6c0b114 ("mm/cma: manage the memory of the CMA area by using the ZONE_MOVABLE")

v4.9.236: Failed to apply! Possible dependencies:
14b468791fa9 ("mm: workingset: move shadow entry tracking to radix tree exceptional tracking") 1c30844d2dfe ("mm: reclaim small amounts of memory when an external fragmentation event occurs") 24512228b7a3 ("mm: do not boost watermarks to avoid fragmentation for the DISCONTIG memory model") 2a2e48854d70 ("mm: vmscan: fix IO/refault regression in cache workingset transition") 31176c781508 ("mm: memcontrol: clean up memory.events counting function") 6bb154504f8b ("mm, page_alloc: spread allocations across zones before introducing fragmentation") 8e675f7af507 ("mm/oom_kill: count global and memory cgroup oom kills") 9d998b4f1e39 ("mm, vmscan: add active list aging tracepoint")
a921444382b4 ("mm: move zone watermark accesses behind an accessor")
cd04ae1e2dc8 ("mm, oom: do not rely on TIF_MEMDIE for memory reserves access") d6622f6365db ("mm/vmscan: more restrictive condition for retry in do_try_to_free_pages") dcec0b60a821 ("mm, vmscan: add mm_vmscan_inactive_list_is_low tracepoint") df0e53d0619e ("mm: memcontrol: re-use global VM event enum")
f7942430e40f ("lib: radix-tree: native accounting of exceptional entries")

v4.4.236: Failed to apply! Possible dependencies:
0b57d6ba0bd1 ("mm/mmap.c: remove redundant local variables for may_expand_vm()") 1170532bb49f ("mm: convert printk(KERN_<LEVEL> to pr_<level>") 5a6e75f8110c ("shmem: prepare huge= mount option and sysfs knob") 756a025f0009 ("mm: coalesce split strings")
84638335900f ("mm: rework virtual memory accounting")
8cee852ec53f ("mm, procfs: breakdown RSS for anon, shmem and file in /proc/pid/status") b46e756f5e47 ("thp: extract khugepaged from mm/huge_memory.c") d07e22597d1d ("mm: mmap: add new /proc tunable for mmap_base ASLR") d977d56ce5b3 ("mm: warn about VmData over RLIMIT_DATA")
d9fe4fab1197 ("x86/mm/pat: Add untrack_pfn_moved for mremap") eca56ff906bd ("mm, shmem: add internal shmem resident memory accounting")

NOTE: The patch will not be queued to stable trees until it is upstream.

How should we proceed with this patch?

Thanks
Sasha