From 39656e83dab918861931ef96e5c41731b0899e56 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 Jul 2019 20:56:49 -0700 Subject: [PATCH] mm: lift the x86_32 PAE version of gup_get_pte to common code The split low/high access is the only non-READ_ONCE version of gup_get_pte that did show up in the various arch implemenations. Lift it to common code and drop the ifdef based arch override. Link: http://lkml.kernel.org/r/20190625143715.1689-4-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Cc: Andrey Konovalov Cc: Benjamin Herrenschmidt Cc: David Miller Cc: James Hogan Cc: Khalid Aziz Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Paul Burton Cc: Paul Mackerras Cc: Ralf Baechle Cc: Rich Felker Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/Kconfig | 1 + arch/x86/include/asm/pgtable-3level.h | 47 ------------------------ arch/x86/kvm/mmu.c | 2 +- mm/Kconfig | 3 ++ mm/gup.c | 53 ++++++++++++++++++++++++--- 5 files changed, 53 insertions(+), 53 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index dce10b18f4bc..71c1f7864434 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -123,6 +123,7 @@ config X86 select GENERIC_STRNLEN_USER select GENERIC_TIME_VSYSCALL select GENERIC_GETTIMEOFDAY + select GUP_GET_PTE_LOW_HIGH if X86_PAE select HARDLOCKUP_CHECK_TIMESTAMP if X86_64 select HAVE_ACPI_APEI if ACPI select HAVE_ACPI_APEI_NMI if ACPI diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index f8b1ad2c3828..e3633795fb22 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -285,53 +285,6 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp) #define __pte_to_swp_entry(pte) (__swp_entry(__pteval_swp_type(pte), \ __pteval_swp_offset(pte))) -#define gup_get_pte gup_get_pte -/* - * WARNING: only to be used in the get_user_pages_fast() implementation. - * - * With get_user_pages_fast(), we walk down the pagetables without taking - * any locks. For this we would like to load the pointers atomically, - * but that is not possible (without expensive cmpxchg8b) on PAE. What - * we do have is the guarantee that a PTE will only either go from not - * present to present, or present to not present or both -- it will not - * switch to a completely different present page without a TLB flush in - * between; something that we are blocking by holding interrupts off. - * - * Setting ptes from not present to present goes: - * - * ptep->pte_high = h; - * smp_wmb(); - * ptep->pte_low = l; - * - * And present to not present goes: - * - * ptep->pte_low = 0; - * smp_wmb(); - * ptep->pte_high = 0; - * - * We must ensure here that the load of pte_low sees 'l' iff pte_high - * sees 'h'. We load pte_high *after* loading pte_low, which ensures we - * don't see an older value of pte_high. *Then* we recheck pte_low, - * which ensures that we haven't picked up a changed pte high. We might - * have gotten rubbish values from pte_low and pte_high, but we are - * guaranteed that pte_low will not have the present bit set *unless* - * it is 'l'. Because get_user_pages_fast() only operates on present ptes - * we're safe. - */ -static inline pte_t gup_get_pte(pte_t *ptep) -{ - pte_t pte; - - do { - pte.pte_low = ptep->pte_low; - smp_rmb(); - pte.pte_high = ptep->pte_high; - smp_rmb(); - } while (unlikely(pte.pte_low != ptep->pte_low)); - - return pte; -} - #include #endif /* _ASM_X86_PGTABLE_3LEVEL_H */ diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 98f6e4f88b04..4a9c63d1c20a 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -650,7 +650,7 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) /* * The idea using the light way get the spte on x86_32 guest is from - * gup_get_pte(arch/x86/mm/gup.c). + * gup_get_pte (mm/gup.c). * * An spte tlb flush may be pending, because kvm_set_pte_rmapp * coalesces them and we are running out of the MMU lock. Therefore diff --git a/mm/Kconfig b/mm/Kconfig index ef6efedc5921..53e2ca54b385 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -762,6 +762,9 @@ config GUP_BENCHMARK See tools/testing/selftests/vm/gup_benchmark.c +config GUP_GET_PTE_LOW_HIGH + bool + config ARCH_HAS_PTE_SPECIAL bool diff --git a/mm/gup.c b/mm/gup.c index 84891c06d485..2093283e4933 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1684,17 +1684,60 @@ struct page *get_dump_page(unsigned long addr) * This code is based heavily on the PowerPC implementation by Nick Piggin. */ #ifdef CONFIG_HAVE_GENERIC_GUP - -#ifndef gup_get_pte +#ifdef CONFIG_GUP_GET_PTE_LOW_HIGH /* - * We assume that the PTE can be read atomically. If this is not the case for - * your architecture, please provide the helper. + * WARNING: only to be used in the get_user_pages_fast() implementation. + * + * With get_user_pages_fast(), we walk down the pagetables without taking any + * locks. For this we would like to load the pointers atomically, but sometimes + * that is not possible (e.g. without expensive cmpxchg8b on x86_32 PAE). What + * we do have is the guarantee that a PTE will only either go from not present + * to present, or present to not present or both -- it will not switch to a + * completely different present page without a TLB flush in between; something + * that we are blocking by holding interrupts off. + * + * Setting ptes from not present to present goes: + * + * ptep->pte_high = h; + * smp_wmb(); + * ptep->pte_low = l; + * + * And present to not present goes: + * + * ptep->pte_low = 0; + * smp_wmb(); + * ptep->pte_high = 0; + * + * We must ensure here that the load of pte_low sees 'l' IFF pte_high sees 'h'. + * We load pte_high *after* loading pte_low, which ensures we don't see an older + * value of pte_high. *Then* we recheck pte_low, which ensures that we haven't + * picked up a changed pte high. We might have gotten rubbish values from + * pte_low and pte_high, but we are guaranteed that pte_low will not have the + * present bit set *unless* it is 'l'. Because get_user_pages_fast() only + * operates on present ptes we're safe. + */ +static inline pte_t gup_get_pte(pte_t *ptep) +{ + pte_t pte; + + do { + pte.pte_low = ptep->pte_low; + smp_rmb(); + pte.pte_high = ptep->pte_high; + smp_rmb(); + } while (unlikely(pte.pte_low != ptep->pte_low)); + + return pte; +} +#else /* CONFIG_GUP_GET_PTE_LOW_HIGH */ +/* + * We require that the PTE can be read atomically. */ static inline pte_t gup_get_pte(pte_t *ptep) { return READ_ONCE(*ptep); } -#endif +#endif /* CONFIG_GUP_GET_PTE_LOW_HIGH */ static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) {