The patch titled sparc64: implement get_user_pages_fast() has been added to the -mm tree. Its filename is sparc64-implement-get_user_pages_fast.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find out what to do about this The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ Subject: sparc64: implement get_user_pages_fast() From: David S. Miller <davem@xxxxxxxxxxxxx> Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx> Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- arch/sparc/mm/Makefile | 2 arch/sparc/mm/gup.c | 181 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 182 insertions(+), 1 deletion(-) diff -puN arch/sparc/mm/Makefile~sparc64-implement-get_user_pages_fast arch/sparc/mm/Makefile --- a/arch/sparc/mm/Makefile~sparc64-implement-get_user_pages_fast +++ a/arch/sparc/mm/Makefile @@ -4,7 +4,7 @@ asflags-y := -ansi ccflags-y := -Werror -obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o +obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o gup.o obj-y += fault_$(BITS).o obj-y += init_$(BITS).o obj-$(CONFIG_SPARC32) += loadmmu.o diff -puN /dev/null arch/sparc/mm/gup.c --- /dev/null +++ a/arch/sparc/mm/gup.c @@ -0,0 +1,181 @@ +/* + * Lockless get_user_pages_fast for sparc, cribbed from powerpc + * + * Copyright (C) 2008 Nick Piggin + * Copyright (C) 2008 Novell Inc. + */ + +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/vmstat.h> +#include <linux/pagemap.h> +#include <linux/rwsem.h> +#include <asm/pgtable.h> + +/* + * The performance critical leaf functions are made noinline otherwise gcc + * inlines everything into a single function which results in too much + * register pressure. + */ +static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + unsigned long mask, result; + pte_t *ptep; + + if (tlb_type == hypervisor) { + result = _PAGE_PRESENT_4V|_PAGE_P_4V; + if (write) + result |= _PAGE_WRITE_4V; + } else { + result = _PAGE_PRESENT_4U|_PAGE_P_4U; + if (write) + result |= _PAGE_WRITE_4U; + } + mask = result | _PAGE_SPECIAL; + + ptep = pte_offset_kernel(&pmd, addr); + do { + struct page *page, *head; + pte_t pte = *ptep; + + if ((pte_val(pte) & mask) != result) + return 0; + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + + /* The hugepage case is simplified on sparc64 because + * we encode the sub-page pfn offsets into the + * hugepage PTEs. We could optimize this in the future + * use page_cache_add_speculative() for the hugepage case. + */ + page = pte_page(pte); + head = compound_head(page); + if (!page_cache_get_speculative(head)) + return 0; + if (unlikely(pte_val(pte) != pte_val(*ptep))) { + put_page(head); + return 0; + } + + pages[*nr] = page; + (*nr)++; + } while (ptep++, addr += PAGE_SIZE, addr != end); + + return 1; +} + +static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + pmd_t *pmdp; + + pmdp = pmd_offset(&pud, addr); + do { + pmd_t pmd = *pmdp; + + next = pmd_addr_end(addr, end); + if (pmd_none(pmd)) + return 0; + if (!gup_pte_range(pmd, addr, next, write, pages, nr)) + return 0; + } while (pmdp++, addr = next, addr != end); + + return 1; +} + +static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + pud_t *pudp; + + pudp = pud_offset(&pgd, addr); + do { + pud_t pud = *pudp; + + next = pud_addr_end(addr, end); + if (pud_none(pud)) + return 0; + if (!gup_pmd_range(pud, addr, next, write, pages, nr)) + return 0; + } while (pudp++, addr = next, addr != end); + + return 1; +} + +int get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages) +{ + struct mm_struct *mm = current->mm; + unsigned long addr, len, end; + unsigned long next; + pgd_t *pgdp; + int nr = 0; + + start &= PAGE_MASK; + addr = start; + len = (unsigned long) nr_pages << PAGE_SHIFT; + end = start + len; + + /* + * XXX: batch / limit 'nr', to avoid large irq off latency + * needs some instrumenting to determine the common sizes used by + * important workloads (eg. DB2), and whether limiting the batch size + * will decrease performance. + * + * It seems like we're in the clear for the moment. Direct-IO is + * the main guy that batches up lots of get_user_pages, and even + * they are limited to 64-at-a-time which is not so many. + */ + /* + * This doesn't prevent pagetable teardown, but does prevent + * the pagetables from being freed on sparc. + * + * So long as we atomically load page table pointers versus teardown, + * we can follow the address down to the the page and take a ref on it. + */ + local_irq_disable(); + + pgdp = pgd_offset(mm, addr); + do { + pgd_t pgd = *pgdp; + + next = pgd_addr_end(addr, end); + if (pgd_none(pgd)) + goto slow; + if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + goto slow; + } while (pgdp++, addr = next, addr != end); + + local_irq_enable(); + + VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT); + return nr; + + { + int ret; + +slow: + local_irq_enable(); + + /* Try to get the remaining pages with get_user_pages */ + start += nr << PAGE_SHIFT; + pages += nr; + + down_read(&mm->mmap_sem); + ret = get_user_pages(current, mm, start, + (end - start) >> PAGE_SHIFT, write, 0, pages, NULL); + up_read(&mm->mmap_sem); + + /* Have to be a bit careful with return values */ + if (nr > 0) { + if (ret < 0) + ret = nr; + else + ret += nr; + } + + return ret; + } +} _ Patches currently in -mm which might be from davem@xxxxxxxxxxxxx are linux-next.patch maintainers-orphan-framerelay-dlci.patch drivers-net-skgec-support-dlink-dge-530t-rev-c1.patch pci-make-the-struct-pci_dev-argument-of-pci_fixup_irqs-const.patch sparc-exec-remove-redundant-addr_limit-assignment.patch sparc64-kill-page-table-quicklists.patch sparc64-use-rcu-page-table-freeing.patch sparc64-add-support-for-_page_special.patch sparc64-implement-get_user_pages_fast.patch kprobes-silence-debug_strict_user_copy_checks=y-warning.patch notifiers-cpu-move-cpu-notifiers-into-cpuh.patch notifiers-net-move-netdevice-notifiers-into-netdeviceh.patch notifiers-sys-move-reboot-notifiers-into-rebooth.patch notifiers-pm-move-pm-notifiers-into-suspendh.patch notifiers-pm-move-pm-notifiers-into-suspendh-update.patch notifiers-vt-move-vt-notifiers-into-vth.patch atomic-use-linux-atomich.patch atomic-move-atomic_add_unless-to-generic-code.patch atomic-cleanup-asm-generic-atomich-inclusion.patch atomic-update-comments-in-atomich.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html