| Message ID | 20220619133851.68184-3-songmuchun@bytedance.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | make hugetlb_optimize_vmemmap compatible with memmap_on_memory | expand |
On Sun, Jun 19, 2022 at 09:38:51PM +0800, Muchun Song wrote: > For now, the feature of hugetlb_free_vmemmap is not compatible with the > feature of memory_hotplug.memmap_on_memory, and hugetlb_free_vmemmap > takes precedence over memory_hotplug.memmap_on_memory. However, someone > wants to make memory_hotplug.memmap_on_memory takes precedence over > hugetlb_free_vmemmap since memmap_on_memory makes it more likely to > succeed memory hotplug in close-to-OOM situations. So the decision > of making hugetlb_free_vmemmap take precedence is not wise and elegant. > The proper approach is to have hugetlb_vmemmap.c do the check whether > the section which the HugeTLB pages belong to can be optimized. If > the section's vmemmap pages are allocated from the added memory block > itself, hugetlb_free_vmemmap should refuse to optimize the vmemmap, > otherwise, do the optimization. Then both kernel parameters are > compatible. So this patch introduces VmemmapSelfHosted to mask any > non-optimizable vmemmap pages. The hugetlb_vmemmap can use this flag > to detect if a vmemmap page can be optimized. > > Signed-off-by: Muchun Song <songmuchun@bytedance.com> > Co-developed-by: Oscar Salvador <osalvador@suse.de> > Signed-off-by: Oscar Salvador <osalvador@suse.de> > --- > Documentation/admin-guide/kernel-parameters.txt | 22 +++++------ > Documentation/admin-guide/sysctl/vm.rst | 5 +-- > include/linux/memory_hotplug.h | 9 ----- > include/linux/page-flags.h | 11 ++++++ > mm/hugetlb_vmemmap.c | 52 +++++++++++++++++++++---- > mm/memory_hotplug.c | 27 ++++++------- > 6 files changed, 79 insertions(+), 47 deletions(-) > > diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt > index 8090130b544b..d740e2ed0e61 100644 > --- a/Documentation/admin-guide/kernel-parameters.txt > +++ b/Documentation/admin-guide/kernel-parameters.txt > @@ -1722,9 +1722,11 @@ > 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. > @@ -3069,10 +3071,12 @@ > [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 > @@ -3082,10 +3086,6 @@ > 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/page-flags.h b/include/linux/page-flags.h > index e66f7aa3191d..2aa5dcbfe468 100644 > --- a/include/linux/page-flags.h > +++ b/include/linux/page-flags.h > @@ -193,6 +193,11 @@ enum pageflags { > > /* Only valid for buddy pages. Used to track pages that are reported */ > PG_reported = PG_uptodate, > + > +#ifdef CONFIG_MEMORY_HOTPLUG > + /* For self-hosted memmap pages */ > + PG_vmemmap_self_hosted = PG_owner_priv_1, > +#endif > }; > > #define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1) > @@ -628,6 +633,12 @@ PAGEFLAG_FALSE(SkipKASanPoison, skip_kasan_poison) > */ > __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) > > +#ifdef CONFIG_MEMORY_HOTPLUG > +PAGEFLAG(VmemmapSelfHosted, vmemmap_self_hosted, PF_ANY) > +#else > +PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) > +#endif > + > /* > * On an anonymous page mapped into a user virtual memory area, > * page->mapping points to its anon_vma, not to a struct address_space; > diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c > index 1089ea8a9c98..73bfbb47f6a4 100644 > --- a/mm/hugetlb_vmemmap.c > +++ b/mm/hugetlb_vmemmap.c > @@ -10,7 +10,7 @@ > */ > #define pr_fmt(fmt) "HugeTLB: " fmt > > -#include <linux/memory_hotplug.h> > +#include <linux/memory.h> > #include "hugetlb_vmemmap.h" > > /* > @@ -97,18 +97,54 @@ int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head) > return ret; > } > > +static unsigned int vmemmap_optimizable_pages(struct hstate *h, > + struct page *head) > +{ > + if (READ_ONCE(vmemmap_optimize_mode) == VMEMMAP_OPTIMIZE_OFF) > + return 0; > + > + if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) { > + unsigned long pfn = page_to_pfn(head); > + > + /* > + * Due to HugeTLB alignment requirements and the vmemmap pages > + * being at the start of the hotplugged memory region in > + * memory_hotplug.memmap_on_memory case. Checking the first > + * vmemmap page's vmemmap if it is marked as VmemmapSelfHosted > + * is sufficient. > + * > + * [ hotplugged memory ] > + * [ section ][...][ section ] > + * [ vmemmap ][ usable memory ] > + * ^ | | | > + * +---+ | | > + * ^ | | > + * +-------+ | > + * ^ | > + * +-------------------------------------------+ > + * > + * Hotplugged memory block never has non-present sections, while > + * boot memory block can have one or more. So pfn_valid() is > + * used to filter out the non-present section which also cannot > + * be memmap_on_memory. > + */ > + pfn = ALIGN_DOWN(pfn, PHYS_PFN(memory_block_size_bytes())); > + if (pfn_valid(pfn) && PageVmemmapSelfHosted(pfn_to_page(pfn))) Although it works, I think PageVmemmapSelfHosted() check for the 1st pfn's vmemmap page is not always reliable. Since we reused PG_owner_priv_1 as PG_vmemmap_self_hosted, the test is noly reliable for vmemmap page's vmemmap page. Other non-vmemmap page can be flagged with PG_owner_priv_1. So this check can be false-positive. Maybe the following code snippet is the solution. Any thoughts? Oscar or David. + if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) { + pmd_t *pmdp, pmd; + struct page *vmemmap_page; + unsigned long vaddr = (unsigned long)head; + + pmdp = pmd_off_k(vaddr); + /* + * The READ_ONCE() is used to stabilize *pmdp in a register or + * on the stack so that it will stop changing under the code. + */ + pmd = READ_ONCE(*pmdp); + if (pmd_leaf(pmd)) + vmemmap_page = pmd_page(pmd) + pte_index(vaddr); + else + vmemmap_page = pte_page(*pte_offset_kernel(pmdp, vaddr)); + /* + * Due to HugeTLB alignment requirements and the vmemmap pages + * being at the start of the hotplugged memory region in + * memory_hotplug.memmap_on_memory case. Checking any vmemmap + * page's vmemmap page if it is marked as VmemmapSelfHosted is + * sufficient. + * + * [ hotplugged memory ] + * [ section ][...][ section ] + * [ vmemmap ][ usable memory ] + * ^ | | | + * +---+ | | + * ^ | | + * +-------+ | + * ^ | + * +-------------------------------------------+ + */ + if (PageVmemmapSelfHosted(vmemmap_page)) + return 0; + } > + 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 = vmemmap_optimizable_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 +235,10 @@ 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 6662b86e9e64..3a59d4e97c03 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 { > @@ -1035,7 +1027,7 @@ int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, > struct zone *zone) > { > unsigned long end_pfn = pfn + nr_pages; > - int ret; > + int ret, i; > > ret = kasan_add_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); > if (ret) > @@ -1043,6 +1035,9 @@ int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, > > move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_UNMOVABLE); > > + for (i = 0; i < nr_pages; i++) > + SetPageVmemmapSelfHosted(pfn_to_page(pfn + i)); > + > /* > * It might be that the vmemmap_pages fully span sections. If that is > * the case, mark those sections online here as otherwise they will be > -- > 2.11.0 > >
On 20.06.22 09:22, Muchun Song wrote: > On Sun, Jun 19, 2022 at 09:38:51PM +0800, Muchun Song wrote: >> For now, the feature of hugetlb_free_vmemmap is not compatible with the >> feature of memory_hotplug.memmap_on_memory, and hugetlb_free_vmemmap >> takes precedence over memory_hotplug.memmap_on_memory. However, someone >> wants to make memory_hotplug.memmap_on_memory takes precedence over >> hugetlb_free_vmemmap since memmap_on_memory makes it more likely to >> succeed memory hotplug in close-to-OOM situations. So the decision >> of making hugetlb_free_vmemmap take precedence is not wise and elegant. >> The proper approach is to have hugetlb_vmemmap.c do the check whether >> the section which the HugeTLB pages belong to can be optimized. If >> the section's vmemmap pages are allocated from the added memory block >> itself, hugetlb_free_vmemmap should refuse to optimize the vmemmap, >> otherwise, do the optimization. Then both kernel parameters are >> compatible. So this patch introduces VmemmapSelfHosted to mask any >> non-optimizable vmemmap pages. The hugetlb_vmemmap can use this flag >> to detect if a vmemmap page can be optimized. >> >> Signed-off-by: Muchun Song <songmuchun@bytedance.com> >> Co-developed-by: Oscar Salvador <osalvador@suse.de> >> Signed-off-by: Oscar Salvador <osalvador@suse.de> >> --- >> Documentation/admin-guide/kernel-parameters.txt | 22 +++++------ >> Documentation/admin-guide/sysctl/vm.rst | 5 +-- >> include/linux/memory_hotplug.h | 9 ----- >> include/linux/page-flags.h | 11 ++++++ >> mm/hugetlb_vmemmap.c | 52 +++++++++++++++++++++---- >> mm/memory_hotplug.c | 27 ++++++------- >> 6 files changed, 79 insertions(+), 47 deletions(-) >> >> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt >> index 8090130b544b..d740e2ed0e61 100644 >> --- a/Documentation/admin-guide/kernel-parameters.txt >> +++ b/Documentation/admin-guide/kernel-parameters.txt >> @@ -1722,9 +1722,11 @@ >> 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. >> @@ -3069,10 +3071,12 @@ >> [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 >> @@ -3082,10 +3086,6 @@ >> 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/page-flags.h b/include/linux/page-flags.h >> index e66f7aa3191d..2aa5dcbfe468 100644 >> --- a/include/linux/page-flags.h >> +++ b/include/linux/page-flags.h >> @@ -193,6 +193,11 @@ enum pageflags { >> >> /* Only valid for buddy pages. Used to track pages that are reported */ >> PG_reported = PG_uptodate, >> + >> +#ifdef CONFIG_MEMORY_HOTPLUG >> + /* For self-hosted memmap pages */ >> + PG_vmemmap_self_hosted = PG_owner_priv_1, >> +#endif >> }; >> >> #define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1) >> @@ -628,6 +633,12 @@ PAGEFLAG_FALSE(SkipKASanPoison, skip_kasan_poison) >> */ >> __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) >> >> +#ifdef CONFIG_MEMORY_HOTPLUG >> +PAGEFLAG(VmemmapSelfHosted, vmemmap_self_hosted, PF_ANY) >> +#else >> +PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) >> +#endif >> + >> /* >> * On an anonymous page mapped into a user virtual memory area, >> * page->mapping points to its anon_vma, not to a struct address_space; >> diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c >> index 1089ea8a9c98..73bfbb47f6a4 100644 >> --- a/mm/hugetlb_vmemmap.c >> +++ b/mm/hugetlb_vmemmap.c >> @@ -10,7 +10,7 @@ >> */ >> #define pr_fmt(fmt) "HugeTLB: " fmt >> >> -#include <linux/memory_hotplug.h> >> +#include <linux/memory.h> >> #include "hugetlb_vmemmap.h" >> >> /* >> @@ -97,18 +97,54 @@ int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head) >> return ret; >> } >> >> +static unsigned int vmemmap_optimizable_pages(struct hstate *h, >> + struct page *head) >> +{ >> + if (READ_ONCE(vmemmap_optimize_mode) == VMEMMAP_OPTIMIZE_OFF) >> + return 0; >> + >> + if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) { >> + unsigned long pfn = page_to_pfn(head); >> + >> + /* >> + * Due to HugeTLB alignment requirements and the vmemmap pages >> + * being at the start of the hotplugged memory region in >> + * memory_hotplug.memmap_on_memory case. Checking the first >> + * vmemmap page's vmemmap if it is marked as VmemmapSelfHosted >> + * is sufficient. >> + * >> + * [ hotplugged memory ] >> + * [ section ][...][ section ] >> + * [ vmemmap ][ usable memory ] >> + * ^ | | | >> + * +---+ | | >> + * ^ | | >> + * +-------+ | >> + * ^ | >> + * +-------------------------------------------+ >> + * >> + * Hotplugged memory block never has non-present sections, while >> + * boot memory block can have one or more. So pfn_valid() is >> + * used to filter out the non-present section which also cannot >> + * be memmap_on_memory. >> + */ >> + pfn = ALIGN_DOWN(pfn, PHYS_PFN(memory_block_size_bytes())); >> + if (pfn_valid(pfn) && PageVmemmapSelfHosted(pfn_to_page(pfn))) > > Although it works, I think PageVmemmapSelfHosted() check for the 1st pfn's > vmemmap page is not always reliable. Since we reused PG_owner_priv_1 > as PG_vmemmap_self_hosted, the test is noly reliable for vmemmap page's > vmemmap page. Other non-vmemmap page can be flagged with PG_owner_priv_1. > So this check can be false-positive. Maybe the following code snippet is > the solution. How could that happen for pages used for backing a vmemmap? > > Any thoughts? Oscar or David. First of all, I think you should really avoid using memory_block_size_bytes(); when using memory_block_size_bytes(), you wouldn't need PageVmemmapSelfHosted(), you can just check if the vmemmap of the page is itself. But I think we should try making this independent of the memory block size. If virt_to_page(page) doesn't work, maybe just traverse the direct map to find the page backing page directly?
On Mon, Jun 20, 2022 at 09:47:22AM +0200, David Hildenbrand wrote: > On 20.06.22 09:22, Muchun Song wrote: > > On Sun, Jun 19, 2022 at 09:38:51PM +0800, Muchun Song wrote: > >> For now, the feature of hugetlb_free_vmemmap is not compatible with the > >> feature of memory_hotplug.memmap_on_memory, and hugetlb_free_vmemmap > >> takes precedence over memory_hotplug.memmap_on_memory. However, someone > >> wants to make memory_hotplug.memmap_on_memory takes precedence over > >> hugetlb_free_vmemmap since memmap_on_memory makes it more likely to > >> succeed memory hotplug in close-to-OOM situations. So the decision > >> of making hugetlb_free_vmemmap take precedence is not wise and elegant. > >> The proper approach is to have hugetlb_vmemmap.c do the check whether > >> the section which the HugeTLB pages belong to can be optimized. If > >> the section's vmemmap pages are allocated from the added memory block > >> itself, hugetlb_free_vmemmap should refuse to optimize the vmemmap, > >> otherwise, do the optimization. Then both kernel parameters are > >> compatible. So this patch introduces VmemmapSelfHosted to mask any > >> non-optimizable vmemmap pages. The hugetlb_vmemmap can use this flag > >> to detect if a vmemmap page can be optimized. > >> > >> Signed-off-by: Muchun Song <songmuchun@bytedance.com> > >> Co-developed-by: Oscar Salvador <osalvador@suse.de> > >> Signed-off-by: Oscar Salvador <osalvador@suse.de> > >> --- > >> Documentation/admin-guide/kernel-parameters.txt | 22 +++++------ > >> Documentation/admin-guide/sysctl/vm.rst | 5 +-- > >> include/linux/memory_hotplug.h | 9 ----- > >> include/linux/page-flags.h | 11 ++++++ > >> mm/hugetlb_vmemmap.c | 52 +++++++++++++++++++++---- > >> mm/memory_hotplug.c | 27 ++++++------- > >> 6 files changed, 79 insertions(+), 47 deletions(-) > >> > >> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt > >> index 8090130b544b..d740e2ed0e61 100644 > >> --- a/Documentation/admin-guide/kernel-parameters.txt > >> +++ b/Documentation/admin-guide/kernel-parameters.txt > >> @@ -1722,9 +1722,11 @@ > >> 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. > >> @@ -3069,10 +3071,12 @@ > >> [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 > >> @@ -3082,10 +3086,6 @@ > >> 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/page-flags.h b/include/linux/page-flags.h > >> index e66f7aa3191d..2aa5dcbfe468 100644 > >> --- a/include/linux/page-flags.h > >> +++ b/include/linux/page-flags.h > >> @@ -193,6 +193,11 @@ enum pageflags { > >> > >> /* Only valid for buddy pages. Used to track pages that are reported */ > >> PG_reported = PG_uptodate, > >> + > >> +#ifdef CONFIG_MEMORY_HOTPLUG > >> + /* For self-hosted memmap pages */ > >> + PG_vmemmap_self_hosted = PG_owner_priv_1, > >> +#endif > >> }; > >> > >> #define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1) > >> @@ -628,6 +633,12 @@ PAGEFLAG_FALSE(SkipKASanPoison, skip_kasan_poison) > >> */ > >> __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) > >> > >> +#ifdef CONFIG_MEMORY_HOTPLUG > >> +PAGEFLAG(VmemmapSelfHosted, vmemmap_self_hosted, PF_ANY) > >> +#else > >> +PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) > >> +#endif > >> + > >> /* > >> * On an anonymous page mapped into a user virtual memory area, > >> * page->mapping points to its anon_vma, not to a struct address_space; > >> diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c > >> index 1089ea8a9c98..73bfbb47f6a4 100644 > >> --- a/mm/hugetlb_vmemmap.c > >> +++ b/mm/hugetlb_vmemmap.c > >> @@ -10,7 +10,7 @@ > >> */ > >> #define pr_fmt(fmt) "HugeTLB: " fmt > >> > >> -#include <linux/memory_hotplug.h> > >> +#include <linux/memory.h> > >> #include "hugetlb_vmemmap.h" > >> > >> /* > >> @@ -97,18 +97,54 @@ int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head) > >> return ret; > >> } > >> > >> +static unsigned int vmemmap_optimizable_pages(struct hstate *h, > >> + struct page *head) > >> +{ > >> + if (READ_ONCE(vmemmap_optimize_mode) == VMEMMAP_OPTIMIZE_OFF) > >> + return 0; > >> + > >> + if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) { > >> + unsigned long pfn = page_to_pfn(head); > >> + > >> + /* > >> + * Due to HugeTLB alignment requirements and the vmemmap pages > >> + * being at the start of the hotplugged memory region in > >> + * memory_hotplug.memmap_on_memory case. Checking the first > >> + * vmemmap page's vmemmap if it is marked as VmemmapSelfHosted > >> + * is sufficient. > >> + * > >> + * [ hotplugged memory ] > >> + * [ section ][...][ section ] > >> + * [ vmemmap ][ usable memory ] > >> + * ^ | | | > >> + * +---+ | | > >> + * ^ | | > >> + * +-------+ | > >> + * ^ | > >> + * +-------------------------------------------+ > >> + * > >> + * Hotplugged memory block never has non-present sections, while > >> + * boot memory block can have one or more. So pfn_valid() is > >> + * used to filter out the non-present section which also cannot > >> + * be memmap_on_memory. > >> + */ > >> + pfn = ALIGN_DOWN(pfn, PHYS_PFN(memory_block_size_bytes())); > >> + if (pfn_valid(pfn) && PageVmemmapSelfHosted(pfn_to_page(pfn))) > > > > Although it works, I think PageVmemmapSelfHosted() check for the 1st pfn's > > vmemmap page is not always reliable. Since we reused PG_owner_priv_1 > > as PG_vmemmap_self_hosted, the test is noly reliable for vmemmap page's > > vmemmap page. Other non-vmemmap page can be flagged with PG_owner_priv_1. > > So this check can be false-positive. Maybe the following code snippet is > > the solution. > > How could that happen for pages used for backing a vmemmap? > It cannot happen for memmap_on_memory case. Howwver, it can happen for other cases. E.g. the 1st pfn (of boot memory block) whose vmemmap page may be flagged as PG_owner_priv_1 (if PG_swapcache is set). Then, the check is false-positive. > > > > Any thoughts? Oscar or David. > > First of all, I think you should really avoid using > memory_block_size_bytes(); when using memory_block_size_bytes(), you > wouldn't need PageVmemmapSelfHosted(), you can just check if the vmemmap > of the page is itself. But I think we should try making this independent > of the memory block size. > Agree. > If virt_to_page(page) doesn't work, maybe just traverse the direct map > to find the page backing page directly? > Yeah, now I have tried to walk page tables to get the backing page. I'll update a new version. Thanks. > -- > Thanks, > > David / dhildenb > >
On Mon, Jun 20, 2022 at 04:29:11PM +0800, Muchun Song wrote: > > > Although it works, I think PageVmemmapSelfHosted() check for the 1st pfn's > > > vmemmap page is not always reliable. Since we reused PG_owner_priv_1 > > > as PG_vmemmap_self_hosted, the test is noly reliable for vmemmap page's > > > vmemmap page. Other non-vmemmap page can be flagged with PG_owner_priv_1. > > > So this check can be false-positive. Maybe the following code snippet is > > > the solution. > > > > How could that happen for pages used for backing a vmemmap? > > > > It cannot happen for memmap_on_memory case. Howwver, it can happen for other > cases. E.g. the 1st pfn (of boot memory block) whose vmemmap page may be flagged > as PG_owner_priv_1 (if PG_swapcache is set). Then, the check is false-positive. If this can really happen, which I am not that sure tbh, maybe a way out would be to just define a new page-type as we did in previous versions of memmap_on_memory. In that way we would not for flags, but for its type. But as I said, I am not entirely sure about the potential fallout of what you mention.
On 20.06.22 10:44, Oscar Salvador wrote: > On Mon, Jun 20, 2022 at 04:29:11PM +0800, Muchun Song wrote: >>>> Although it works, I think PageVmemmapSelfHosted() check for the 1st pfn's >>>> vmemmap page is not always reliable. Since we reused PG_owner_priv_1 >>>> as PG_vmemmap_self_hosted, the test is noly reliable for vmemmap page's >>>> vmemmap page. Other non-vmemmap page can be flagged with PG_owner_priv_1. >>>> So this check can be false-positive. Maybe the following code snippet is >>>> the solution. >>> >>> How could that happen for pages used for backing a vmemmap? >>> >> >> It cannot happen for memmap_on_memory case. Howwver, it can happen for other >> cases. E.g. the 1st pfn (of boot memory block) whose vmemmap page may be flagged >> as PG_owner_priv_1 (if PG_swapcache is set). Then, the check is false-positive. > > If this can really happen, which I am not that sure tbh, maybe a way out would be > to just define a new page-type as we did in previous versions of memmap_on_memory. > In that way we would not for flags, but for its type. > > But as I said, I am not entirely sure about the potential fallout of what you mention. We are talking about the memmap of a page, who's page content is the memmap of pages actually exposed to other users (file-backed, anonymous, whatsoever). In other words, while setting PG_swapcache on the memmap of a page exposed to the user is possible, it shouldn't be possible for the memmap of the page "hosting" these memmaps. I know, it's confusing and I keep confusing myself. I tried creating a picture and it doesn't really clarify the situation :D
On Mon, Jun 20, 2022 at 10:44:40AM +0200, Oscar Salvador wrote: > On Mon, Jun 20, 2022 at 04:29:11PM +0800, Muchun Song wrote: > > > > Although it works, I think PageVmemmapSelfHosted() check for the 1st pfn's > > > > vmemmap page is not always reliable. Since we reused PG_owner_priv_1 > > > > as PG_vmemmap_self_hosted, the test is noly reliable for vmemmap page's > > > > vmemmap page. Other non-vmemmap page can be flagged with PG_owner_priv_1. > > > > So this check can be false-positive. Maybe the following code snippet is > > > > the solution. > > > > > > How could that happen for pages used for backing a vmemmap? > > > > > > > It cannot happen for memmap_on_memory case. Howwver, it can happen for other > > cases. E.g. the 1st pfn (of boot memory block) whose vmemmap page may be flagged > > as PG_owner_priv_1 (if PG_swapcache is set). Then, the check is false-positive. > > If this can really happen, which I am not that sure tbh, maybe a way out would be I need to clarify this only can be happened by using this approach implemented in this patch. For a boot memory block, the vemmmap pages are not slef-hosted. So the 1st pfn (of this memory block) can be allocated to other users. e.g. an anonymous page with PG_swapcache set. In this patch, ALIGN_DOWN(pfn, PHYS_PFN(memory_block_size_bytes())) will located on this anonymous page, then the check is false-positive. [ boot memory block ] [ section ][...][ section ] [ usable memory ] > to just define a new page-type as we did in previous versions of memmap_on_memory. > In that way we would not for flags, but for its type. > I think we do not need to introduced a new flag, we just make sure the page passed to PageVmemmapSelfHosted() is a backing page for vmemmap. Then we cannot incur false-positive. The feasible solution is walking page tables to find a vmemmap page's backing page. Thanks. > But as I said, I am not entirely sure about the potential fallout of what you mention. > > > -- > Oscar Salvador > SUSE Labs >
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 8090130b544b..d740e2ed0e61 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1722,9 +1722,11 @@ 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. @@ -3069,10 +3071,12 @@ [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 @@ -3082,10 +3086,6 @@ 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/page-flags.h b/include/linux/page-flags.h index e66f7aa3191d..2aa5dcbfe468 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -193,6 +193,11 @@ enum pageflags { /* Only valid for buddy pages. Used to track pages that are reported */ PG_reported = PG_uptodate, + +#ifdef CONFIG_MEMORY_HOTPLUG + /* For self-hosted memmap pages */ + PG_vmemmap_self_hosted = PG_owner_priv_1, +#endif }; #define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1) @@ -628,6 +633,12 @@ PAGEFLAG_FALSE(SkipKASanPoison, skip_kasan_poison) */ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) +#ifdef CONFIG_MEMORY_HOTPLUG +PAGEFLAG(VmemmapSelfHosted, vmemmap_self_hosted, PF_ANY) +#else +PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) +#endif + /* * On an anonymous page mapped into a user virtual memory area, * page->mapping points to its anon_vma, not to a struct address_space; diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 1089ea8a9c98..73bfbb47f6a4 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -10,7 +10,7 @@ */ #define pr_fmt(fmt) "HugeTLB: " fmt -#include <linux/memory_hotplug.h> +#include <linux/memory.h> #include "hugetlb_vmemmap.h" /* @@ -97,18 +97,54 @@ int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head) return ret; } +static unsigned int vmemmap_optimizable_pages(struct hstate *h, + struct page *head) +{ + if (READ_ONCE(vmemmap_optimize_mode) == VMEMMAP_OPTIMIZE_OFF) + return 0; + + if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) { + unsigned long pfn = page_to_pfn(head); + + /* + * Due to HugeTLB alignment requirements and the vmemmap pages + * being at the start of the hotplugged memory region in + * memory_hotplug.memmap_on_memory case. Checking the first + * vmemmap page's vmemmap if it is marked as VmemmapSelfHosted + * is sufficient. + * + * [ hotplugged memory ] + * [ section ][...][ section ] + * [ vmemmap ][ usable memory ] + * ^ | | | + * +---+ | | + * ^ | | + * +-------+ | + * ^ | + * +-------------------------------------------+ + * + * Hotplugged memory block never has non-present sections, while + * boot memory block can have one or more. So pfn_valid() is + * used to filter out the non-present section which also cannot + * be memmap_on_memory. + */ + pfn = ALIGN_DOWN(pfn, PHYS_PFN(memory_block_size_bytes())); + if (pfn_valid(pfn) && PageVmemmapSelfHosted(pfn_to_page(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 = vmemmap_optimizable_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 +235,10 @@ 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 6662b86e9e64..3a59d4e97c03 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 { @@ -1035,7 +1027,7 @@ int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, struct zone *zone) { unsigned long end_pfn = pfn + nr_pages; - int ret; + int ret, i; ret = kasan_add_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); if (ret) @@ -1043,6 +1035,9 @@ int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_UNMOVABLE); + for (i = 0; i < nr_pages; i++) + SetPageVmemmapSelfHosted(pfn_to_page(pfn + i)); + /* * It might be that the vmemmap_pages fully span sections. If that is * the case, mark those sections online here as otherwise they will be