On Wed, 6 Aug 2025 14:35:15 +0200, david@xxxxxxxxxx wrote: > On 05.08.25 03:24, Alex Williamson wrote: > > Objections were raised to adding this helper to common code with only a > > single user and dubious generalism. Pull it back into subsystem code. > > > > Link: https://lore.kernel.org/all/CAHk-=whhYRMS7Xc9k_JBdrGvp++JLmU0T2xXEgn046hWrj7q8Q@xxxxxxxxxxxxxx/ > > Cc: David Hildenbrand <david@xxxxxxxxxx> > > Cc: Jason Gunthorpe <jgg@xxxxxxxxxx> > > Cc: Li Zhe <lizhe.67@xxxxxxxxxxxxx> > > Signed-off-by: Alex Williamson <alex.williamson@xxxxxxxxxx> > > --- > > So, I took the original patch and > * moved the code to mm_inline.h (sounds like a better fit) > * Tweaked the patch description > * Tweaked the documentation and turned it into proper kerneldoc > * Made the function return "size_t" as well > * Use the page_to_section() trick to avoid nth_page(). > > Only compile-tested so far. Still running it through some cross compiles. > > > From 36d67849bfdbc184990f21464c53585d35648616 Mon Sep 17 00:00:00 2001 > From: Li Zhe <lizhe.67@xxxxxxxxxxxxx> > Date: Thu, 10 Jul 2025 16:53:51 +0800 > Subject: [PATCH] mm: introduce num_pages_contiguous() > > Let's add a simple helper for determining the number of contiguous pages > that represent contiguous PFNs. > > In an ideal world, this helper would be simpler or not even required. > Unfortunately, on some configs we still have to maintain (SPARSEMEM > without VMEMMAP), the memmap is allocated per memory section, and we might > run into weird corner cases of false positives when blindly testing for > contiguous pages only. > > One example of such false positives would be a memory section-sized hole > that does not have a memmap. The surrounding memory sections might get > "struct pages" that are contiguous, but the PFNs are actually not. > > This helper will, for example, be useful for determining contiguous PFNs > in a GUP result, to batch further operations across returned "struct > page"s. VFIO will utilize this interface to accelerate the VFIO DMA map > process. > > Implementation based on Linus' suggestions to avoid new usage of > nth_page() where avoidable. > > Suggested-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> > Suggested-by: Jason Gunthorpe <jgg@xxxxxxxx> > Signed-off-by: Li Zhe <lizhe.67@xxxxxxxxxxxxx> > Co-developed-by: David Hildenbrand <david@xxxxxxxxxx> > Signed-off-by: David Hildenbrand <david@xxxxxxxxxx> > --- > include/linux/mm.h | 7 ++++++- > include/linux/mm_inline.h | 35 +++++++++++++++++++++++++++++++++++ > 2 files changed, 41 insertions(+), 1 deletion(-) > > diff --git a/include/linux/mm.h b/include/linux/mm.h > index fa538feaa8d95..2852bcd792745 100644 > --- a/include/linux/mm.h > +++ b/include/linux/mm.h > @@ -1759,7 +1759,12 @@ static inline unsigned long page_to_section(const struct page *page) > { > return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; > } > -#endif > +#else /* !SECTION_IN_PAGE_FLAGS */ > +static inline unsigned long page_to_section(const struct page *page) > +{ > + return 0; > +} > +#endif /* SECTION_IN_PAGE_FLAGS */ > > /** > * folio_pfn - Return the Page Frame Number of a folio. > diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h > index 89b518ff097e6..58cb99b69f432 100644 > --- a/include/linux/mm_inline.h > +++ b/include/linux/mm_inline.h > @@ -616,4 +616,39 @@ static inline bool vma_has_recency(struct vm_area_struct *vma) > return true; > } > > +/** > + * num_pages_contiguous() - determine the number of contiguous pages > + * that represent contiguous PFNs > + * @pages: an array of page pointers > + * @nr_pages: length of the array, at least 1 > + * > + * Determine the number of contiguous pages that represent contiguous PFNs > + * in @pages, starting from the first page. > + * > + * In kernel configs where contiguous pages might not imply contiguous PFNs > + * over memory section boundaries, this function will stop at the memory > + * section boundary. > + * > + * Returns the number of contiguous pages. > + */ > +static inline size_t num_pages_contiguous(struct page **pages, size_t nr_pages) > +{ > + struct page *cur_page = pages[0]; > + unsigned long section = page_to_section(cur_page); > + size_t i; > + > + for (i = 1; i < nr_pages; i++) { > + if (++cur_page != pages[i]) > + break; > + /* > + * In unproblematic kernel configs, page_to_section() == 0 and > + * the whole check will get optimized out. > + */ > + if (page_to_section(cur_page) != section) > + break; > + } > + > + return i; > +} > + > #endif I sincerely appreciate your thoughtful revisions to this patch. The code looks great. Based on this patch, I reran the performance tests for the VFIO optimizations. The results show no significant change from the previous data. Since num_pages_contiguous() is now defined in mm_inline.h, the second patch "vfio/type1: optimize vfio_pin_pages_remote()" in this series needs to include that header to resolve the build error. diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 1136d7ac6b59..af98cb94153c 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -37,6 +37,7 @@ #include <linux/vfio.h> #include <linux/workqueue.h> #include <linux/notifier.h> +#include <linux/mm_inline.h> #include "vfio.h" #define DRIVER_VERSION "0.2" Thanks, Zhe
