On Wed, Jun 15, 2022 at 11:51:49AM +0200, David Hildenbrand wrote:
> An easier/future-proof approach might simply be flagging the vmemmap
> pages as being special. We reuse page flags for that, which don't have
> semantics yet (i.e., PG_reserved indicates a boot-time allocation via
> memblock).
The first versions of memmap_on_memory [1] introduced a new page type
to represent such pages, not sure if that is what you mean, e.g:
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index f91cb8898ff0..75f302a532f9 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -708,6 +708,7 @@ PAGEFLAG_FALSE(DoubleMap)
#define PG_kmemcg 0x00000200
#define PG_table 0x00000400
#define PG_guard 0x00000800
+#define PG_vmemmap 0x00001000
#define PageType(page, flag) \
((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE)
@@ -764,6 +765,24 @@ PAGE_TYPE_OPS(Table, table)
*/
PAGE_TYPE_OPS(Guard, guard)
+/*
+ * Vmemmap pages refers to those pages that are used to create the memmap
+ * array, and reside within the same memory range that was hotppluged, so
+ * they are self-hosted. (see include/linux/memory_hotplug.h)
+ */
+PAGE_TYPE_OPS(Vmemmap, vmemmap)
+static __always_inline void SetPageVmemmap(struct page *page)
+{
+ __SetPageVmemmap(page);
+ __SetPageReserved(page);
+}
+
+static __always_inline void ClearPageVmemmap(struct page *page)
+{
+ __ClearPageVmemmap(page);
+ __ClearPageReserved(page);
+}
[1] https://patchwork.kernel.org/project/linux-mm/patch/20190725160207.19579-3-osalvador@xxxxxxx/
>
> You'd walk the applicable vmemmap pages you want to optimize and check
> if they are marked as special. You don't have to walk all but can
> optimize: memmap_on_memory uses a vmemmap size that's at least PMD_SIZE.
> So it's sufficient to check a single vmemmap page inside a PMD_SIZE
> vmemmap range.
>
>
> > Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
> > ---
> > Documentation/admin-guide/kernel-parameters.txt | 22 +++++++++----------
> > Documentation/admin-guide/sysctl/vm.rst | 5 ++---
> > include/linux/memory_hotplug.h | 9 --------
> > include/linux/mmzone.h | 17 +++++++++++++++
> > mm/hugetlb_vmemmap.c | 28 ++++++++++++++++++-------
> > mm/memory_hotplug.c | 22 +++++++------------
> > mm/sparse.c | 8 +++++++
> > 7 files changed, 66 insertions(+), 45 deletions(-)
> >
> > diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> > index c087f578d9d8..5359ffb04a84 100644
> > --- a/Documentation/admin-guide/kernel-parameters.txt
> > +++ b/Documentation/admin-guide/kernel-parameters.txt
> > @@ -1730,9 +1730,11 @@
> > Built with CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=y,
> > the default is on.
> >
> > - This is not compatible with memory_hotplug.memmap_on_memory.
> > - If both parameters are enabled, hugetlb_free_vmemmap takes
> > - precedence over memory_hotplug.memmap_on_memory.
> > + Note that the vmemmap pages may be allocated from the added
> > + memory block itself when memory_hotplug.memmap_on_memory is
> > + enabled, those vmemmap pages cannot be optimized even if this
> > + feature is enabled. Other vmemmap pages not allocated from
> > + the added memory block itself do not be affected.
> >
> > hung_task_panic=
> > [KNL] Should the hung task detector generate panics.
> > @@ -3077,10 +3079,12 @@
> > [KNL,X86,ARM] Boolean flag to enable this feature.
> > Format: {on | off (default)}
> > When enabled, runtime hotplugged memory will
> > - allocate its internal metadata (struct pages)
> > - from the hotadded memory which will allow to
> > - hotadd a lot of memory without requiring
> > - additional memory to do so.
> > + allocate its internal metadata (struct pages,
> > + those vmemmap pages cannot be optimized even
> > + if hugetlb_free_vmemmap is enabled) from the
> > + hotadded memory which will allow to hotadd a
> > + lot of memory without requiring additional
> > + memory to do so.
> > This feature is disabled by default because it
> > has some implication on large (e.g. GB)
> > allocations in some configurations (e.g. small
> > @@ -3090,10 +3094,6 @@
> > Note that even when enabled, there are a few cases where
> > the feature is not effective.
> >
> > - This is not compatible with hugetlb_free_vmemmap. If
> > - both parameters are enabled, hugetlb_free_vmemmap takes
> > - precedence over memory_hotplug.memmap_on_memory.
> > -
> > memtest= [KNL,X86,ARM,M68K,PPC,RISCV] Enable memtest
> > Format: <integer>
> > default : 0 <disable>
> > diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst
> > index 5c9aa171a0d3..d7374a1e8ac9 100644
> > --- a/Documentation/admin-guide/sysctl/vm.rst
> > +++ b/Documentation/admin-guide/sysctl/vm.rst
> > @@ -565,9 +565,8 @@ See Documentation/admin-guide/mm/hugetlbpage.rst
> > hugetlb_optimize_vmemmap
> > ========================
> >
> > -This knob is not available when memory_hotplug.memmap_on_memory (kernel parameter)
> > -is configured or the size of 'struct page' (a structure defined in
> > -include/linux/mm_types.h) is not power of two (an unusual system config could
> > +This knob is not available when the size of 'struct page' (a structure defined
> > +in include/linux/mm_types.h) is not power of two (an unusual system config could
> > result in this).
> >
> > Enable (set to 1) or disable (set to 0) the feature of optimizing vmemmap pages
> > diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
> > index 20d7edf62a6a..e0b2209ab71c 100644
> > --- a/include/linux/memory_hotplug.h
> > +++ b/include/linux/memory_hotplug.h
> > @@ -351,13 +351,4 @@ void arch_remove_linear_mapping(u64 start, u64 size);
> > extern bool mhp_supports_memmap_on_memory(unsigned long size);
> > #endif /* CONFIG_MEMORY_HOTPLUG */
> >
> > -#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
> > -bool mhp_memmap_on_memory(void);
> > -#else
> > -static inline bool mhp_memmap_on_memory(void)
> > -{
> > - return false;
> > -}
> > -#endif
> > -
> > #endif /* __LINUX_MEMORY_HOTPLUG_H */
> > diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> > index 2cf2a76535ab..607a4fcabbd4 100644
> > --- a/include/linux/mmzone.h
> > +++ b/include/linux/mmzone.h
> > @@ -1434,6 +1434,7 @@ extern size_t mem_section_usage_size(void);
> > MAPPER(IS_ONLINE) \
> > MAPPER(IS_EARLY) \
> > MAPPER(TAINT_ZONE_DEVICE, CONFIG_ZONE_DEVICE) \
> > + MAPPER(CANNOT_OPTIMIZE_VMEMMAP, CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP) \
> > MAPPER(MAP_LAST_BIT)
> >
> > #define __SECTION_SHIFT_FLAG_MAPPER_0(x)
> > @@ -1471,6 +1472,22 @@ static inline struct page *__section_mem_map_addr(struct mem_section *section)
> > return (struct page *)map;
> > }
> >
> > +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
> > +static inline void section_mark_cannot_optimize_vmemmap(struct mem_section *ms)
> > +{
> > + ms->section_mem_map |= SECTION_CANNOT_OPTIMIZE_VMEMMAP;
> > +}
> > +
> > +static inline int section_cannot_optimize_vmemmap(struct mem_section *ms)
> > +{
> > + return (ms && (ms->section_mem_map & SECTION_CANNOT_OPTIMIZE_VMEMMAP));
> > +}
> > +#else
> > +static inline void section_mark_cannot_optimize_vmemmap(struct mem_section *ms)
> > +{
> > +}
> > +#endif
> > +
> > static inline int present_section(struct mem_section *section)
> > {
> > return (section && (section->section_mem_map & SECTION_MARKED_PRESENT));
> > diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
> > index fcd9f7872064..f12170520337 100644
> > --- a/mm/hugetlb_vmemmap.c
> > +++ b/mm/hugetlb_vmemmap.c
> > @@ -97,18 +97,32 @@ int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head)
> > return ret;
> > }
> >
> > +static unsigned int optimizable_vmemmap_pages(struct hstate *h,
> > + struct page *head)
> > +{
> > + unsigned long pfn = page_to_pfn(head);
> > + unsigned long end = pfn + pages_per_huge_page(h);
> > +
> > + if (READ_ONCE(vmemmap_optimize_mode) == VMEMMAP_OPTIMIZE_OFF)
> > + return 0;
> > +
> > + for (; pfn < end; pfn += PAGES_PER_SECTION) {
> > + if (section_cannot_optimize_vmemmap(__pfn_to_section(pfn)))
> > + return 0;
> > + }
> > +
> > + return hugetlb_optimize_vmemmap_pages(h);
> > +}
> > +
> > void hugetlb_vmemmap_free(struct hstate *h, struct page *head)
> > {
> > unsigned long vmemmap_addr = (unsigned long)head;
> > unsigned long vmemmap_end, vmemmap_reuse, vmemmap_pages;
> >
> > - vmemmap_pages = hugetlb_optimize_vmemmap_pages(h);
> > + vmemmap_pages = optimizable_vmemmap_pages(h, head);
> > if (!vmemmap_pages)
> > return;
> >
> > - if (READ_ONCE(vmemmap_optimize_mode) == VMEMMAP_OPTIMIZE_OFF)
> > - return;
> > -
> > static_branch_inc(&hugetlb_optimize_vmemmap_key);
> >
> > vmemmap_addr += RESERVE_VMEMMAP_SIZE;
> > @@ -199,10 +213,10 @@ static struct ctl_table hugetlb_vmemmap_sysctls[] = {
> > static __init int hugetlb_vmemmap_sysctls_init(void)
> > {
> > /*
> > - * If "memory_hotplug.memmap_on_memory" is enabled or "struct page"
> > - * crosses page boundaries, the vmemmap pages cannot be optimized.
> > + * If "struct page" crosses page boundaries, the vmemmap pages cannot
> > + * be optimized.
> > */
> > - if (!mhp_memmap_on_memory() && is_power_of_2(sizeof(struct page)))
> > + if (is_power_of_2(sizeof(struct page)))
> > register_sysctl_init("vm", hugetlb_vmemmap_sysctls);
> >
> > return 0;
> > diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> > index 3b360eda933f..7309694c4dee 100644
> > --- a/mm/memory_hotplug.c
> > +++ b/mm/memory_hotplug.c
> > @@ -43,30 +43,22 @@
> > #include "shuffle.h"
> >
> > #ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
> > -static int memmap_on_memory_set(const char *val, const struct kernel_param *kp)
> > -{
> > - if (hugetlb_optimize_vmemmap_enabled())
> > - return 0;
> > - return param_set_bool(val, kp);
> > -}
> > -
> > -static const struct kernel_param_ops memmap_on_memory_ops = {
> > - .flags = KERNEL_PARAM_OPS_FL_NOARG,
> > - .set = memmap_on_memory_set,
> > - .get = param_get_bool,
> > -};
> > -
> > /*
> > * memory_hotplug.memmap_on_memory parameter
> > */
> > static bool memmap_on_memory __ro_after_init;
> > -module_param_cb(memmap_on_memory, &memmap_on_memory_ops, &memmap_on_memory, 0444);
> > +module_param(memmap_on_memory, bool, 0444);
> > MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug");
> >
> > -bool mhp_memmap_on_memory(void)
> > +static inline bool mhp_memmap_on_memory(void)
> > {
> > return memmap_on_memory;
> > }
> > +#else
> > +static inline bool mhp_memmap_on_memory(void)
> > +{
> > + return false;
> > +}
> > #endif
> >
> > enum {
> > diff --git a/mm/sparse.c b/mm/sparse.c
> > index cb3bfae64036..1f353bf9ea6b 100644
> > --- a/mm/sparse.c
> > +++ b/mm/sparse.c
> > @@ -913,6 +913,14 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn,
> > ms = __nr_to_section(section_nr);
> > set_section_nid(section_nr, nid);
> > __section_mark_present(ms, section_nr);
> > + /*
> > + * Mark whole section as non-optimizable once there is a subsection
> > + * whose vmemmap pages are allocated from alternative allocator. The
> > + * early section is always optimizable since the early section's
> > + * vmemmap pages do not consider partially being populated.
> > + */
> > + if (!early_section(ms) && altmap)
> > + section_mark_cannot_optimize_vmemmap(ms);
> >
> > /* Align memmap to section boundary in the subsection case */
> > if (section_nr_to_pfn(section_nr) != start_pfn)
>
>
> --
> Thanks,
>
> David / dhildenb
>
>
--
Oscar Salvador
SUSE Labs
