From patchwork Fri Nov 14 17:10:02 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Will Deacon X-Patchwork-Id: 40839 Return-Path: X-Original-To: linaro@patches.linaro.org Delivered-To: linaro@patches.linaro.org Received: from mail-la0-f70.google.com (mail-la0-f70.google.com [209.85.215.70]) by ip-10-151-82-157.ec2.internal (Postfix) with ESMTPS id EB175244FC for ; Fri, 14 Nov 2014 17:11:04 +0000 (UTC) Received: by mail-la0-f70.google.com with SMTP id ge10sf10633159lab.9 for ; Fri, 14 Nov 2014 09:11:03 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:mime-version:delivered-to:from:to:cc:subject :date:message-id:sender:precedence:list-id:x-original-sender :x-original-authentication-results:mailing-list:list-post:list-help :list-archive:list-unsubscribe; bh=d0YNWrlcHIQmknLk+WtsNjQvrT3X4zeLIAxBc5iR+OI=; b=VtvwuqeIz4RAQdIsQsfSLBzY+SwcOdT92kiZAFTyhhmWg1B7FHN9GppbzAkkeOZtt4 WSSddhIodAZrcexBnVPBPfaGzHyLfXXMhgQnefDYON0OvO4CPBhqh/KbUgjqfls99FQE VDukTXgyDbbG8/dx9NlnFaEDwy1c/p5iWadlVyrXgpUm0Y4Zi7n89jvv5TU2tIZy7dXe ptzVpmIsAk5bgFjCa59vORmvDCsqm22rhRBg7sUrlmBDpi6g1JgIwU5coLH6gkfcudaE v0Ki+rTqMMhHYtAtmzd/jzjw1nno3NIwXiYb2XAaoaji3wureqvt5dwDapkoniqWads+ X3dg== X-Gm-Message-State: ALoCoQmSespzfVSLULCLl5uv0c5cLchoUjIAmPipUwQngu9Np8Ru4c5kB+uXrKZhinaZYrre0FNw X-Received: by 10.112.166.102 with SMTP id zf6mr719781lbb.12.1415985063818; Fri, 14 Nov 2014 09:11:03 -0800 (PST) MIME-Version: 1.0 X-BeenThere: patchwork-forward@linaro.org Received: by 10.152.23.4 with SMTP id i4ls1009801laf.59.gmail; Fri, 14 Nov 2014 09:11:03 -0800 (PST) X-Received: by 10.152.243.37 with SMTP id wv5mr5276000lac.10.1415985063440; Fri, 14 Nov 2014 09:11:03 -0800 (PST) Received: from mail-la0-f44.google.com (mail-la0-f44.google.com. [209.85.215.44]) by mx.google.com with ESMTPS id n1si37837093laj.114.2014.11.14.09.11.03 for (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Fri, 14 Nov 2014 09:11:03 -0800 (PST) Received-SPF: pass (google.com: domain of patch+caf_=patchwork-forward=linaro.org@linaro.org designates 209.85.215.44 as permitted sender) client-ip=209.85.215.44; Received: by mail-la0-f44.google.com with SMTP id hz20so5334142lab.3 for ; Fri, 14 Nov 2014 09:11:03 -0800 (PST) X-Received: by 10.112.235.196 with SMTP id uo4mr9214482lbc.66.1415985063290; Fri, 14 Nov 2014 09:11:03 -0800 (PST) X-Forwarded-To: patchwork-forward@linaro.org X-Forwarded-For: patch@linaro.org patchwork-forward@linaro.org Delivered-To: patch@linaro.org Received: by 10.112.184.201 with SMTP id ew9csp798711lbc; Fri, 14 Nov 2014 09:11:02 -0800 (PST) X-Received: by 10.70.136.66 with SMTP id py2mr11676041pdb.48.1415985061589; Fri, 14 Nov 2014 09:11:01 -0800 (PST) Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id te6si28734523pbc.227.2014.11.14.09.11.00 for ; Fri, 14 Nov 2014 09:11:01 -0800 (PST) Received-SPF: none (google.com: linux-kernel-owner@vger.kernel.org does not designate permitted sender hosts) client-ip=209.132.180.67; Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1161542AbaKNRKt (ORCPT + 26 others); Fri, 14 Nov 2014 12:10:49 -0500 Received: from cam-admin0.cambridge.arm.com ([217.140.96.50]:33520 "EHLO cam-admin0.cambridge.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1161512AbaKNRKr (ORCPT ); Fri, 14 Nov 2014 12:10:47 -0500 Received: from edgewater-inn.cambridge.arm.com (edgewater-inn.cambridge.arm.com [10.1.203.36]) by cam-admin0.cambridge.arm.com (8.12.6/8.12.6) with ESMTP id sAEHA0wo023314; Fri, 14 Nov 2014 17:10:00 GMT Received: by edgewater-inn.cambridge.arm.com (Postfix, from userid 1000) id EA9F01AE01E4; Fri, 14 Nov 2014 17:10:05 +0000 (GMT) From: Will Deacon To: linux-kernel@vger.kernel.org Cc: catalin.marinas@arm.com, Will Deacon , Linus Torvalds , Benjamin Herrenschmidt , Peter Zijlstra , Russell King - ARM Linux , Michal Simek Subject: [PATCH] mmu_gather: move minimal range calculations into generic code Date: Fri, 14 Nov 2014 17:10:02 +0000 Message-Id: <1415985002-28144-1-git-send-email-will.deacon@arm.com> X-Mailer: git-send-email 2.1.1 Sender: linux-kernel-owner@vger.kernel.org Precedence: list List-ID: X-Mailing-List: linux-kernel@vger.kernel.org X-Removed-Original-Auth: Dkim didn't pass. X-Original-Sender: will.deacon@arm.com X-Original-Authentication-Results: mx.google.com; spf=pass (google.com: domain of patch+caf_=patchwork-forward=linaro.org@linaro.org designates 209.85.215.44 as permitted sender) smtp.mail=patch+caf_=patchwork-forward=linaro.org@linaro.org Mailing-list: list patchwork-forward@linaro.org; contact patchwork-forward+owners@linaro.org X-Google-Group-Id: 836684582541 List-Post: , List-Help: , List-Archive: List-Unsubscribe: , On architectures with hardware broadcasting of TLB invalidation messages , it makes sense to reduce the range of the mmu_gather structure when unmapping page ranges based on the dirty address information passed to tlb_remove_tlb_entry. arm64 already does this by directly manipulating the start/end fields of the gather structure, but this confuses the generic code which does not expect these fields to change and can end up calculating invalid, negative ranges when forcing a flush in zap_pte_range. This patch moves the minimal range calculation out of the arm64 code and into the generic implementation, simplifying zap_pte_range in the process (which no longer needs to care about start/end, since they will point to the appropriate ranges already). With the range being tracked by core code, the need_flush flag is dropped in favour of checking that the end of the range has actually been set. Cc: Linus Torvalds Cc: Benjamin Herrenschmidt Cc: Peter Zijlstra Cc: Russell King - ARM Linux Cc: Michal Simek Signed-off-by: Will Deacon --- Hi all, Just a heads up that I plan to drop this into -next early next week as part of the arm64 queue for 3.19. It's been on LKML in two parts already, but please holler if you spot any issues. Will arch/arm64/include/asm/tlb.h | 67 ++------------------------------------ arch/microblaze/include/asm/tlb.h | 3 +- arch/powerpc/include/asm/pgalloc.h | 3 +- arch/powerpc/include/asm/tlb.h | 1 + arch/powerpc/mm/hugetlbpage.c | 2 -- include/asm-generic/tlb.h | 57 ++++++++++++++++++++++++++------ mm/memory.c | 30 +++++------------ 7 files changed, 63 insertions(+), 100 deletions(-) diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index a82c0c5c8b52..c028fe37456f 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -19,10 +19,6 @@ #ifndef __ASM_TLB_H #define __ASM_TLB_H -#define __tlb_remove_pmd_tlb_entry __tlb_remove_pmd_tlb_entry - -#include - #include #include @@ -37,71 +33,22 @@ static inline void __tlb_remove_table(void *_table) #define tlb_remove_entry(tlb, entry) tlb_remove_page(tlb, entry) #endif /* CONFIG_HAVE_RCU_TABLE_FREE */ -/* - * There's three ways the TLB shootdown code is used: - * 1. Unmapping a range of vmas. See zap_page_range(), unmap_region(). - * tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called. - * 2. Unmapping all vmas. See exit_mmap(). - * tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called. - * Page tables will be freed. - * 3. Unmapping argument pages. See shift_arg_pages(). - * tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called. - */ +#include + static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->fullmm) { flush_tlb_mm(tlb->mm); - } else if (tlb->end > 0) { + } else { struct vm_area_struct vma = { .vm_mm = tlb->mm, }; flush_tlb_range(&vma, tlb->start, tlb->end); - tlb->start = TASK_SIZE; - tlb->end = 0; - } -} - -static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr) -{ - if (!tlb->fullmm) { - tlb->start = min(tlb->start, addr); - tlb->end = max(tlb->end, addr + PAGE_SIZE); - } -} - -/* - * Memorize the range for the TLB flush. - */ -static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, - unsigned long addr) -{ - tlb_add_flush(tlb, addr); -} - -/* - * In the case of tlb vma handling, we can optimise these away in the - * case where we're doing a full MM flush. When we're doing a munmap, - * the vmas are adjusted to only cover the region to be torn down. - */ -static inline void tlb_start_vma(struct mmu_gather *tlb, - struct vm_area_struct *vma) -{ - if (!tlb->fullmm) { - tlb->start = TASK_SIZE; - tlb->end = 0; } } -static inline void tlb_end_vma(struct mmu_gather *tlb, - struct vm_area_struct *vma) -{ - if (!tlb->fullmm) - tlb_flush(tlb); -} - static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { pgtable_page_dtor(pte); - tlb_add_flush(tlb, addr); tlb_remove_entry(tlb, pte); } @@ -109,7 +56,6 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr) { - tlb_add_flush(tlb, addr); tlb_remove_entry(tlb, virt_to_page(pmdp)); } #endif @@ -118,15 +64,8 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp, unsigned long addr) { - tlb_add_flush(tlb, addr); tlb_remove_entry(tlb, virt_to_page(pudp)); } #endif -static inline void __tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, - unsigned long address) -{ - tlb_add_flush(tlb, address); -} - #endif diff --git a/arch/microblaze/include/asm/tlb.h b/arch/microblaze/include/asm/tlb.h index 8aa97817cc8c..99b6ded54849 100644 --- a/arch/microblaze/include/asm/tlb.h +++ b/arch/microblaze/include/asm/tlb.h @@ -14,7 +14,6 @@ #define tlb_flush(tlb) flush_tlb_mm((tlb)->mm) #include -#include #ifdef CONFIG_MMU #define tlb_start_vma(tlb, vma) do { } while (0) @@ -22,4 +21,6 @@ #define __tlb_remove_tlb_entry(tlb, pte, address) do { } while (0) #endif +#include + #endif /* _ASM_MICROBLAZE_TLB_H */ diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h index e9a9f60e596d..fc3ee06eab87 100644 --- a/arch/powerpc/include/asm/pgalloc.h +++ b/arch/powerpc/include/asm/pgalloc.h @@ -3,7 +3,6 @@ #ifdef __KERNEL__ #include -#include #ifdef CONFIG_PPC_BOOK3E extern void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address); @@ -14,6 +13,8 @@ static inline void tlb_flush_pgtable(struct mmu_gather *tlb, } #endif /* !CONFIG_PPC_BOOK3E */ +extern void tlb_remove_table(struct mmu_gather *tlb, void *table); + #ifdef CONFIG_PPC64 #include #else diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index e2b428b0f7ba..20733fa518ae 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -27,6 +27,7 @@ #define tlb_start_vma(tlb, vma) do { } while (0) #define tlb_end_vma(tlb, vma) do { } while (0) +#define __tlb_remove_tlb_entry __tlb_remove_tlb_entry extern void tlb_flush(struct mmu_gather *tlb); diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 7e70ae968e5f..6a4a5fcb9730 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -517,8 +517,6 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif for (i = 0; i < num_hugepd; i++, hpdp++) hpdp->pd = 0; - tlb->need_flush = 1; - #ifdef CONFIG_PPC_FSL_BOOK3E hugepd_free(tlb, hugepte); #else diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 5672d7ea1fa0..08848050922e 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -96,10 +96,9 @@ struct mmu_gather { #endif unsigned long start; unsigned long end; - unsigned int need_flush : 1, /* Did free PTEs */ /* we are in the middle of an operation to clear * a full mm and can make some optimizations */ - fullmm : 1, + unsigned int fullmm : 1, /* we have performed an operation which * requires a complete flush of the tlb */ need_flush_all : 1; @@ -128,16 +127,54 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) tlb_flush_mmu(tlb); } +static inline void __tlb_adjust_range(struct mmu_gather *tlb, + unsigned long address) +{ + tlb->start = min(tlb->start, address); + tlb->end = max(tlb->end, address + PAGE_SIZE); +} + +static inline void __tlb_reset_range(struct mmu_gather *tlb) +{ + tlb->start = TASK_SIZE; + tlb->end = 0; +} + +/* + * In the case of tlb vma handling, we can optimise these away in the + * case where we're doing a full MM flush. When we're doing a munmap, + * the vmas are adjusted to only cover the region to be torn down. + */ +#ifndef tlb_start_vma +#define tlb_start_vma(tlb, vma) do { } while (0) +#endif + +#define __tlb_end_vma(tlb, vma) \ + do { \ + if (!tlb->fullmm && tlb->end) { \ + tlb_flush(tlb); \ + __tlb_reset_range(tlb); \ + } \ + } while (0) + +#ifndef tlb_end_vma +#define tlb_end_vma __tlb_end_vma +#endif + +#ifndef __tlb_remove_tlb_entry +#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) +#endif + /** * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation. * - * Record the fact that pte's were really umapped in ->need_flush, so we can - * later optimise away the tlb invalidate. This helps when userspace is - * unmapping already-unmapped pages, which happens quite a lot. + * Record the fact that pte's were really unmapped by updating the range, + * so we can later optimise away the tlb invalidate. This helps when + * userspace is unmapping already-unmapped pages, which happens quite a lot. */ #define tlb_remove_tlb_entry(tlb, ptep, address) \ do { \ - tlb->need_flush = 1; \ + __tlb_adjust_range(tlb, address); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) @@ -151,27 +188,27 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address) \ do { \ - tlb->need_flush = 1; \ + __tlb_adjust_range(tlb, address); \ __tlb_remove_pmd_tlb_entry(tlb, pmdp, address); \ } while (0) #define pte_free_tlb(tlb, ptep, address) \ do { \ - tlb->need_flush = 1; \ + __tlb_adjust_range(tlb, address); \ __pte_free_tlb(tlb, ptep, address); \ } while (0) #ifndef __ARCH_HAS_4LEVEL_HACK #define pud_free_tlb(tlb, pudp, address) \ do { \ - tlb->need_flush = 1; \ + __tlb_adjust_range(tlb, address); \ __pud_free_tlb(tlb, pudp, address); \ } while (0) #endif #define pmd_free_tlb(tlb, pmdp, address) \ do { \ - tlb->need_flush = 1; \ + __tlb_adjust_range(tlb, address); \ __pmd_free_tlb(tlb, pmdp, address); \ } while (0) diff --git a/mm/memory.c b/mm/memory.c index 3e503831e042..8b1c1d2e7c67 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -220,9 +220,6 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long /* Is it from 0 to ~0? */ tlb->fullmm = !(start | (end+1)); tlb->need_flush_all = 0; - tlb->start = start; - tlb->end = end; - tlb->need_flush = 0; tlb->local.next = NULL; tlb->local.nr = 0; tlb->local.max = ARRAY_SIZE(tlb->__pages); @@ -232,15 +229,20 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long #ifdef CONFIG_HAVE_RCU_TABLE_FREE tlb->batch = NULL; #endif + + __tlb_reset_range(tlb); } static void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) { - tlb->need_flush = 0; + if (!tlb->end) + return; + tlb_flush(tlb); #ifdef CONFIG_HAVE_RCU_TABLE_FREE tlb_table_flush(tlb); #endif + __tlb_reset_range(tlb); } static void tlb_flush_mmu_free(struct mmu_gather *tlb) @@ -256,8 +258,6 @@ static void tlb_flush_mmu_free(struct mmu_gather *tlb) void tlb_flush_mmu(struct mmu_gather *tlb) { - if (!tlb->need_flush) - return; tlb_flush_mmu_tlbonly(tlb); tlb_flush_mmu_free(tlb); } @@ -292,7 +292,7 @@ int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) { struct mmu_gather_batch *batch; - VM_BUG_ON(!tlb->need_flush); + VM_BUG_ON(!tlb->end); batch = tlb->active; batch->pages[batch->nr++] = page; @@ -359,8 +359,6 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) { struct mmu_table_batch **batch = &tlb->batch; - tlb->need_flush = 1; - /* * When there's less then two users of this mm there cannot be a * concurrent page-table walk. @@ -1186,20 +1184,8 @@ again: arch_leave_lazy_mmu_mode(); /* Do the actual TLB flush before dropping ptl */ - if (force_flush) { - unsigned long old_end; - - /* - * Flush the TLB just for the previous segment, - * then update the range to be the remaining - * TLB range. - */ - old_end = tlb->end; - tlb->end = addr; + if (force_flush) tlb_flush_mmu_tlbonly(tlb); - tlb->start = addr; - tlb->end = old_end; - } pte_unmap_unlock(start_pte, ptl); /*