From 7a581204b1fa4fed233ed3b7ffcf6847cc383dbc Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 7 Jun 2024 10:37:10 +0200 Subject: [PATCH] mm/highmem: reimplement totalhigh_pages() by walking zones Patch series "mm/highmem: don't track highmem pages manually". Let's remove highmem special-casing from adjust_managed_page_count(), to result in less confusion why memblock manually adjusts totalram_pages, and __free_pages_core() only adjusts the zone's managed pages -- what about the highmem pages that adjust_managed_page_count() updates? Now, we only maintain totalram_pages and a zone's managed pages independent of highmem support. We can derive the number of highmem pages simply by looking at the relevant zone's managed pages. I don't think there is any particular fast path that needs a maximum-efficient totalhigh_pages() implementation. Note that highmem memory is currently initialized using free_highmem_page()->free_reserved_page(), not __free_pages_core(). In the future we might want to also use __free_pages_core() to initialize highmem memory, to make that less special, and consider moving totalram_pages updates into __free_pages_core() [1], so we can just use adjust_managed_page_count() in there as well. Booting a simple kernel in QEMU reveals no highmem accounting change: Before: Memory: 3095448K/3145208K available (14802K kernel code, 2073K rwdata, 5000K rodata, 740K init, 556K bss, 49760K reserved, 0K cma-reserved, 2244488K highmem) After: Memory: 3095276K/3145208K available (14802K kernel code, 2073K rwdata, 5000K rodata, 740K init, 556K bss, 49932K reserved, 0K cma-reserved, 2244488K highmem) [1] https://lkml.kernel.org/r/20240601133402.2675-1-richard.weiyang@gmail.com This patch (of 2): Can we get rid of the highmem ifdef in adjust_managed_page_count()? Likely yes: we don't have that many totalhigh_pages() users, and they all don't seem to be very performance critical. So let's implement totalhigh_pages() like nr_free_highpages(), collecting information from all zones. This is now similar to what we do in si_meminfo_node() to collect the per-node highmem page count. In the common case (single node, 3-4 zones), we really shouldn't care. We could optimize a bit further (only walk ZONE_HIGHMEM and ZONE_MOVABLE if required), but there doesn't seem a real need for that. [david@redhat.com: fix build bot complaint] Link: https://lkml.kernel.org/r/b57e5bc4-eb72-40e3-add4-57dfa6e03df6@redhat.com Link: https://lkml.kernel.org/r/20240607083711.62833-1-david@redhat.com Link: https://lkml.kernel.org/r/20240607083711.62833-2-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Wei Yang Reviewed-by: Oscar Salvador Signed-off-by: Andrew Morton --- include/linux/highmem-internal.h | 9 ++------- mm/highmem.c | 17 ++++++++++++++--- mm/page_alloc.c | 4 ---- 3 files changed, 16 insertions(+), 14 deletions(-) diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index a3028e400a9c..65f865fbbac0 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -132,7 +132,7 @@ static inline void __kunmap_atomic(const void *addr) } unsigned int __nr_free_highpages(void); -extern atomic_long_t _totalhigh_pages; +unsigned long __totalhigh_pages(void); static inline unsigned int nr_free_highpages(void) { @@ -141,12 +141,7 @@ static inline unsigned int nr_free_highpages(void) static inline unsigned long totalhigh_pages(void) { - return (unsigned long)atomic_long_read(&_totalhigh_pages); -} - -static inline void totalhigh_pages_add(long count) -{ - atomic_long_add(count, &_totalhigh_pages); + return __totalhigh_pages(); } static inline bool is_kmap_addr(const void *x) diff --git a/mm/highmem.c b/mm/highmem.c index bd48ba445dd4..b14771fb05ed 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -111,9 +111,6 @@ static inline wait_queue_head_t *get_pkmap_wait_queue_head(unsigned int color) } #endif -atomic_long_t _totalhigh_pages __read_mostly; -EXPORT_SYMBOL(_totalhigh_pages); - unsigned int __nr_free_highpages(void) { struct zone *zone; @@ -127,6 +124,20 @@ unsigned int __nr_free_highpages(void) return pages; } +unsigned long __totalhigh_pages(void) +{ + unsigned long pages = 0; + struct zone *zone; + + for_each_populated_zone(zone) { + if (is_highmem(zone)) + pages += zone_managed_pages(zone); + } + + return pages; +} +EXPORT_SYMBOL(__totalhigh_pages); + static int pkmap_count[LAST_PKMAP]; static __cacheline_aligned_in_smp DEFINE_SPINLOCK(kmap_lock); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9ecf99190ea2..804c171a3c3a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5762,10 +5762,6 @@ void adjust_managed_page_count(struct page *page, long count) { atomic_long_add(count, &page_zone(page)->managed_pages); totalram_pages_add(count); -#ifdef CONFIG_HIGHMEM - if (PageHighMem(page)) - totalhigh_pages_add(count); -#endif } EXPORT_SYMBOL(adjust_managed_page_count);