| Message ID | 20240611030812.9582-1-richard.weiyang@gmail.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | mm/mm_init.c: print mem_init info after defer_init is done | expand |
On 11.06.24 05:08, Wei Yang wrote: > Current call flow looks like this: > > start_kernel > mm_core_init > mem_init > mem_init_print_info > rest_init > kernel_init > kernel_init_freeable > page_alloc_init_late > deferred_init_memmap > > If CONFIG_DEFERRED_STRUCT_PAGE_INIT, the time mem_init_print_info() > calls, pages are not totally initialized and freed to buddy. > > This has one issue > > * nr_free_pages() just contains partial free pages in the system, > which is not we expect. > Maybe mention that this will also help changing totalpage accounting. > Let's print the mem info after defer_init is done. > > Signed-off-by: Wei Yang <richard.weiyang@gmail.com> > CC: David Hildenbrand <david@redhat.com> > --- > mm/mm_init.c | 104 +++++++++++++++++++++++++-------------------------- > 1 file changed, 52 insertions(+), 52 deletions(-) > > diff --git a/mm/mm_init.c b/mm/mm_init.c > index f72b852bd5b8..34a6de20ef77 100644 > --- a/mm/mm_init.c > +++ b/mm/mm_init.c > @@ -2322,6 +2322,57 @@ void set_zone_contiguous(struct zone *zone) > zone->contiguous = true; > } > > +static void __init mem_init_print_info(void) Can you avoid all that churn simply by doing a static void __init mem_init_print_info(void); somewhere at the beginning of this file? > +{ > + unsigned long physpages, codesize, datasize, rosize, bss_size; > + unsigned long init_code_size, init_data_size; > + > + physpages = get_num_physpages(); > + codesize = _etext - _stext; > + datasize = _edata - _sdata; > + rosize = __end_rodata - __start_rodata; > + bss_size = __bss_stop - __bss_start; > + init_data_size = __init_end - __init_begin; > + init_code_size = _einittext - _sinittext; > + > + /* > + * Detect special cases and adjust section sizes accordingly: > + * 1) .init.* may be embedded into .data sections > + * 2) .init.text.* may be out of [__init_begin, __init_end], > + * please refer to arch/tile/kernel/vmlinux.lds.S. > + * 3) .rodata.* may be embedded into .text or .data sections. > + */ > +#define adj_init_size(start, end, size, pos, adj) \ > + do { \ > + if (&start[0] <= &pos[0] && &pos[0] < &end[0] && size > adj) \ > + size -= adj; \ > + } while (0) > + > + adj_init_size(__init_begin, __init_end, init_data_size, > + _sinittext, init_code_size); > + adj_init_size(_stext, _etext, codesize, _sinittext, init_code_size); > + adj_init_size(_sdata, _edata, datasize, __init_begin, init_data_size); > + adj_init_size(_stext, _etext, codesize, __start_rodata, rosize); > + adj_init_size(_sdata, _edata, datasize, __start_rodata, rosize); > + > +#undef adj_init_size > + > + pr_info("Memory: %luK/%luK available (%luK kernel code, %luK rwdata, %luK rodata, %luK init, %luK bss, %luK reserved, %luK cma-reserved" > +#ifdef CONFIG_HIGHMEM > + ", %luK highmem" > +#endif > + ")\n", > + K(nr_free_pages()), K(physpages), > + codesize / SZ_1K, datasize / SZ_1K, rosize / SZ_1K, > + (init_data_size + init_code_size) / SZ_1K, bss_size / SZ_1K, > + K(physpages - totalram_pages() - totalcma_pages), > + K(totalcma_pages) > +#ifdef CONFIG_HIGHMEM > + , K(totalhigh_pages()) > +#endif > + ); > +} > + > void __init page_alloc_init_late(void) > { > struct zone *zone; > @@ -2348,6 +2399,7 @@ void __init page_alloc_init_late(void) > files_maxfiles_init(); > #endif > Maybe add a comment like /* Accounting of total+free memory is stable at this point. */ > + mem_init_print_info();
On Tue, Jun 11, 2024 at 04:26:56PM +0200, David Hildenbrand wrote: >On 11.06.24 05:08, Wei Yang wrote: >> Current call flow looks like this: >> >> start_kernel >> mm_core_init >> mem_init >> mem_init_print_info >> rest_init >> kernel_init >> kernel_init_freeable >> page_alloc_init_late >> deferred_init_memmap >> >> If CONFIG_DEFERRED_STRUCT_PAGE_INIT, the time mem_init_print_info() >> calls, pages are not totally initialized and freed to buddy. >> >> This has one issue >> >> * nr_free_pages() just contains partial free pages in the system, >> which is not we expect. >> > >Maybe mention that this will also help changing totalpage accounting. > Sure. >> Let's print the mem info after defer_init is done. >> >> Signed-off-by: Wei Yang <richard.weiyang@gmail.com> >> CC: David Hildenbrand <david@redhat.com> >> --- >> mm/mm_init.c | 104 +++++++++++++++++++++++++-------------------------- >> 1 file changed, 52 insertions(+), 52 deletions(-) >> >> diff --git a/mm/mm_init.c b/mm/mm_init.c >> index f72b852bd5b8..34a6de20ef77 100644 >> --- a/mm/mm_init.c >> +++ b/mm/mm_init.c >> @@ -2322,6 +2322,57 @@ void set_zone_contiguous(struct zone *zone) >> zone->contiguous = true; >> } >> +static void __init mem_init_print_info(void) > >Can you avoid all that churn simply by doing a > >static void __init mem_init_print_info(void); > >somewhere at the beginning of this file? Ok, if this is preferred. > >> +{ >> + unsigned long physpages, codesize, datasize, rosize, bss_size; >> + unsigned long init_code_size, init_data_size; >> + >> + physpages = get_num_physpages(); >> + codesize = _etext - _stext; >> + datasize = _edata - _sdata; >> + rosize = __end_rodata - __start_rodata; >> + bss_size = __bss_stop - __bss_start; >> + init_data_size = __init_end - __init_begin; >> + init_code_size = _einittext - _sinittext; >> + >> + /* >> + * Detect special cases and adjust section sizes accordingly: >> + * 1) .init.* may be embedded into .data sections >> + * 2) .init.text.* may be out of [__init_begin, __init_end], >> + * please refer to arch/tile/kernel/vmlinux.lds.S. >> + * 3) .rodata.* may be embedded into .text or .data sections. >> + */ >> +#define adj_init_size(start, end, size, pos, adj) \ >> + do { \ >> + if (&start[0] <= &pos[0] && &pos[0] < &end[0] && size > adj) \ >> + size -= adj; \ >> + } while (0) >> + >> + adj_init_size(__init_begin, __init_end, init_data_size, >> + _sinittext, init_code_size); >> + adj_init_size(_stext, _etext, codesize, _sinittext, init_code_size); >> + adj_init_size(_sdata, _edata, datasize, __init_begin, init_data_size); >> + adj_init_size(_stext, _etext, codesize, __start_rodata, rosize); >> + adj_init_size(_sdata, _edata, datasize, __start_rodata, rosize); >> + >> +#undef adj_init_size >> + >> + pr_info("Memory: %luK/%luK available (%luK kernel code, %luK rwdata, %luK rodata, %luK init, %luK bss, %luK reserved, %luK cma-reserved" >> +#ifdef CONFIG_HIGHMEM >> + ", %luK highmem" >> +#endif >> + ")\n", >> + K(nr_free_pages()), K(physpages), >> + codesize / SZ_1K, datasize / SZ_1K, rosize / SZ_1K, >> + (init_data_size + init_code_size) / SZ_1K, bss_size / SZ_1K, >> + K(physpages - totalram_pages() - totalcma_pages), >> + K(totalcma_pages) >> +#ifdef CONFIG_HIGHMEM >> + , K(totalhigh_pages()) >> +#endif >> + ); >> +} >> + >> void __init page_alloc_init_late(void) >> { >> struct zone *zone; >> @@ -2348,6 +2399,7 @@ void __init page_alloc_init_late(void) >> files_maxfiles_init(); >> #endif > >Maybe add a comment like > >/* Accounting of total+free memory is stable at this point. */ > >> + mem_init_print_info(); > > >-- >Cheers, > >David / dhildenb
diff --git a/mm/mm_init.c b/mm/mm_init.c index f72b852bd5b8..34a6de20ef77 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2322,6 +2322,57 @@ void set_zone_contiguous(struct zone *zone) zone->contiguous = true; } +static void __init mem_init_print_info(void) +{ + unsigned long physpages, codesize, datasize, rosize, bss_size; + unsigned long init_code_size, init_data_size; + + physpages = get_num_physpages(); + codesize = _etext - _stext; + datasize = _edata - _sdata; + rosize = __end_rodata - __start_rodata; + bss_size = __bss_stop - __bss_start; + init_data_size = __init_end - __init_begin; + init_code_size = _einittext - _sinittext; + + /* + * Detect special cases and adjust section sizes accordingly: + * 1) .init.* may be embedded into .data sections + * 2) .init.text.* may be out of [__init_begin, __init_end], + * please refer to arch/tile/kernel/vmlinux.lds.S. + * 3) .rodata.* may be embedded into .text or .data sections. + */ +#define adj_init_size(start, end, size, pos, adj) \ + do { \ + if (&start[0] <= &pos[0] && &pos[0] < &end[0] && size > adj) \ + size -= adj; \ + } while (0) + + adj_init_size(__init_begin, __init_end, init_data_size, + _sinittext, init_code_size); + adj_init_size(_stext, _etext, codesize, _sinittext, init_code_size); + adj_init_size(_sdata, _edata, datasize, __init_begin, init_data_size); + adj_init_size(_stext, _etext, codesize, __start_rodata, rosize); + adj_init_size(_sdata, _edata, datasize, __start_rodata, rosize); + +#undef adj_init_size + + pr_info("Memory: %luK/%luK available (%luK kernel code, %luK rwdata, %luK rodata, %luK init, %luK bss, %luK reserved, %luK cma-reserved" +#ifdef CONFIG_HIGHMEM + ", %luK highmem" +#endif + ")\n", + K(nr_free_pages()), K(physpages), + codesize / SZ_1K, datasize / SZ_1K, rosize / SZ_1K, + (init_data_size + init_code_size) / SZ_1K, bss_size / SZ_1K, + K(physpages - totalram_pages() - totalcma_pages), + K(totalcma_pages) +#ifdef CONFIG_HIGHMEM + , K(totalhigh_pages()) +#endif + ); +} + void __init page_alloc_init_late(void) { struct zone *zone; @@ -2348,6 +2399,7 @@ void __init page_alloc_init_late(void) files_maxfiles_init(); #endif + mem_init_print_info(); buffer_init(); /* Discard memblock private memory */ @@ -2666,57 +2718,6 @@ static void __init report_meminit(void) pr_info("mem auto-init: clearing system memory may take some time...\n"); } -static void __init mem_init_print_info(void) -{ - unsigned long physpages, codesize, datasize, rosize, bss_size; - unsigned long init_code_size, init_data_size; - - physpages = get_num_physpages(); - codesize = _etext - _stext; - datasize = _edata - _sdata; - rosize = __end_rodata - __start_rodata; - bss_size = __bss_stop - __bss_start; - init_data_size = __init_end - __init_begin; - init_code_size = _einittext - _sinittext; - - /* - * Detect special cases and adjust section sizes accordingly: - * 1) .init.* may be embedded into .data sections - * 2) .init.text.* may be out of [__init_begin, __init_end], - * please refer to arch/tile/kernel/vmlinux.lds.S. - * 3) .rodata.* may be embedded into .text or .data sections. - */ -#define adj_init_size(start, end, size, pos, adj) \ - do { \ - if (&start[0] <= &pos[0] && &pos[0] < &end[0] && size > adj) \ - size -= adj; \ - } while (0) - - adj_init_size(__init_begin, __init_end, init_data_size, - _sinittext, init_code_size); - adj_init_size(_stext, _etext, codesize, _sinittext, init_code_size); - adj_init_size(_sdata, _edata, datasize, __init_begin, init_data_size); - adj_init_size(_stext, _etext, codesize, __start_rodata, rosize); - adj_init_size(_sdata, _edata, datasize, __start_rodata, rosize); - -#undef adj_init_size - - pr_info("Memory: %luK/%luK available (%luK kernel code, %luK rwdata, %luK rodata, %luK init, %luK bss, %luK reserved, %luK cma-reserved" -#ifdef CONFIG_HIGHMEM - ", %luK highmem" -#endif - ")\n", - K(nr_free_pages()), K(physpages), - codesize / SZ_1K, datasize / SZ_1K, rosize / SZ_1K, - (init_data_size + init_code_size) / SZ_1K, bss_size / SZ_1K, - K(physpages - totalram_pages() - totalcma_pages), - K(totalcma_pages) -#ifdef CONFIG_HIGHMEM - , K(totalhigh_pages()) -#endif - ); -} - /* * Set up kernel memory allocators */ @@ -2737,7 +2738,6 @@ void __init mm_core_init(void) kmsan_init_shadow(); stack_depot_early_init(); mem_init(); - mem_init_print_info(); kmem_cache_init(); /* * page_owner must be initialized after buddy is ready, and also after
Current call flow looks like this: start_kernel mm_core_init mem_init mem_init_print_info rest_init kernel_init kernel_init_freeable page_alloc_init_late deferred_init_memmap If CONFIG_DEFERRED_STRUCT_PAGE_INIT, the time mem_init_print_info() calls, pages are not totally initialized and freed to buddy. This has one issue * nr_free_pages() just contains partial free pages in the system, which is not we expect. Let's print the mem info after defer_init is done. Signed-off-by: Wei Yang <richard.weiyang@gmail.com> CC: David Hildenbrand <david@redhat.com> --- mm/mm_init.c | 104 +++++++++++++++++++++++++-------------------------- 1 file changed, 52 insertions(+), 52 deletions(-)