From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id D5E7BC433F5 for ; Tue, 28 Sep 2021 02:35:52 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id BB7E061156 for ; Tue, 28 Sep 2021 02:35:52 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S238628AbhI1Ch2 (ORCPT ); Mon, 27 Sep 2021 22:37:28 -0400 Received: from szxga01-in.huawei.com ([45.249.212.187]:12734 "EHLO szxga01-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S238564AbhI1Ch1 (ORCPT ); Mon, 27 Sep 2021 22:37:27 -0400 Received: from dggemv703-chm.china.huawei.com (unknown [172.30.72.56]) by szxga01-in.huawei.com (SkyGuard) with ESMTP id 4HJNr55ThSzWXtd; Tue, 28 Sep 2021 10:34:29 +0800 (CST) Received: from kwepemm600017.china.huawei.com (7.193.23.234) by dggemv703-chm.china.huawei.com (10.3.19.46) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2308.8; Tue, 28 Sep 2021 10:35:43 +0800 Received: from [10.174.179.234] (10.174.179.234) by kwepemm600017.china.huawei.com (7.193.23.234) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2308.8; Tue, 28 Sep 2021 10:35:43 +0800 Subject: Re: [PATCH -next] riscv/vdso: Add support for time namespaces To: Paul Walmsley , Palmer Dabbelt , Palmer Dabbelt , Albert Ou References: <20210901032025.2529454-1-tongtiangen@huawei.com> CC: , From: tongtiangen Message-ID: <6cdb42c0-9b80-1d09-f309-5691f0013a96@huawei.com> Date: Tue, 28 Sep 2021 10:35:42 +0800 User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:45.0) Gecko/20100101 Thunderbird/45.7.1 MIME-Version: 1.0 In-Reply-To: <20210901032025.2529454-1-tongtiangen@huawei.com> Content-Type: text/plain; charset="windows-1252"; format=flowed Content-Transfer-Encoding: 7bit X-Originating-IP: [10.174.179.234] X-ClientProxiedBy: dggems705-chm.china.huawei.com (10.3.19.182) To kwepemm600017.china.huawei.com (7.193.23.234) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org kindly ping. On 2021/9/1 11:20, Tong Tiangen wrote: > Implement generic vdso time namespace support which also enables time > namespaces for riscv. This is quite similar to what arm64 does. > > selftest/timens test result: > 1..10 > ok 1 Passed for CLOCK_BOOTTIME (syscall) > ok 2 Passed for CLOCK_BOOTTIME (vdso) > ok 3 # SKIP CLOCK_BOOTTIME_ALARM isn't supported > ok 4 # SKIP CLOCK_BOOTTIME_ALARM isn't supported > ok 5 Passed for CLOCK_MONOTONIC (syscall) > ok 6 Passed for CLOCK_MONOTONIC (vdso) > ok 7 Passed for CLOCK_MONOTONIC_COARSE (syscall) > ok 8 Passed for CLOCK_MONOTONIC_COARSE (vdso) > ok 9 Passed for CLOCK_MONOTONIC_RAW (syscall) > ok 10 Passed for CLOCK_MONOTONIC_RAW (vdso) > # Totals: pass:8 fail:0 xfail:0 xpass:0 skip:2 error:0 > > Signed-off-by: Tong Tiangen > --- > This patch is based on patchset: > https://lore.kernel.org/lkml/20210901024621.2528797-1-tongtiangen@huawei.com/ > > arch/riscv/Kconfig | 1 + > arch/riscv/include/asm/page.h | 2 + > arch/riscv/include/asm/vdso.h | 2 +- > arch/riscv/include/asm/vdso/gettimeofday.h | 7 + > arch/riscv/kernel/vdso.c | 250 ++++++++++++++++----- > arch/riscv/kernel/vdso/vdso.lds.S | 3 + > 6 files changed, 211 insertions(+), 54 deletions(-) > > diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig > index aac669a6c3d8..7b0eff8a7eef 100644 > --- a/arch/riscv/Kconfig > +++ b/arch/riscv/Kconfig > @@ -61,6 +61,7 @@ config RISCV > select GENERIC_SCHED_CLOCK > select GENERIC_SMP_IDLE_THREAD > select GENERIC_TIME_VSYSCALL if MMU && 64BIT > + select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO > select HANDLE_DOMAIN_IRQ > select HAVE_ARCH_AUDITSYSCALL > select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL > diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h > index 109c97e991a6..b3e5ff0125fe 100644 > --- a/arch/riscv/include/asm/page.h > +++ b/arch/riscv/include/asm/page.h > @@ -157,6 +157,8 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x); > #define page_to_bus(page) (page_to_phys(page)) > #define phys_to_page(paddr) (pfn_to_page(phys_to_pfn(paddr))) > > +#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) > + > #ifdef CONFIG_FLATMEM > #define pfn_valid(pfn) \ > (((pfn) >= ARCH_PFN_OFFSET) && (((pfn) - ARCH_PFN_OFFSET) < max_mapnr)) > diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h > index 34210b22ba91..bee9514104f7 100644 > --- a/arch/riscv/include/asm/vdso.h > +++ b/arch/riscv/include/asm/vdso.h > @@ -14,7 +14,7 @@ > */ > #ifdef CONFIG_MMU > > -#define __VVAR_PAGES 1 > +#define __VVAR_PAGES 2 > > #ifndef __ASSEMBLY__ > > diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h > index f839f16e0d2a..77d9c2f721c4 100644 > --- a/arch/riscv/include/asm/vdso/gettimeofday.h > +++ b/arch/riscv/include/asm/vdso/gettimeofday.h > @@ -76,6 +76,13 @@ static __always_inline const struct vdso_data *__arch_get_vdso_data(void) > return _vdso_data; > } > > +#ifdef CONFIG_TIME_NS > +static __always_inline > +const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) > +{ > + return _timens_data; > +} > +#endif > #endif /* !__ASSEMBLY__ */ > > #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ > diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c > index b70956d80408..a9436a65161a 100644 > --- a/arch/riscv/kernel/vdso.c > +++ b/arch/riscv/kernel/vdso.c > @@ -13,6 +13,7 @@ > #include > #include > #include > +#include > > #ifdef CONFIG_GENERIC_TIME_VSYSCALL > #include > @@ -25,14 +26,12 @@ extern char vdso_start[], vdso_end[]; > > enum vvar_pages { > VVAR_DATA_PAGE_OFFSET, > + VVAR_TIMENS_PAGE_OFFSET, > VVAR_NR_PAGES, > }; > > #define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) > > -static unsigned int vdso_pages __ro_after_init; > -static struct page **vdso_pagelist __ro_after_init; > - > /* > * The vDSO data page. > */ > @@ -42,83 +41,228 @@ static union { > } vdso_data_store __page_aligned_data; > struct vdso_data *vdso_data = &vdso_data_store.data; > > -static int __init vdso_init(void) > +struct __vdso_info { > + const char *name; > + const char *vdso_code_start; > + const char *vdso_code_end; > + unsigned long vdso_pages; > + /* Data Mapping */ > + struct vm_special_mapping *dm; > + /* Code Mapping */ > + struct vm_special_mapping *cm; > +}; > + > +static struct __vdso_info vdso_info __ro_after_init = { > + .name = "vdso", > + .vdso_code_start = vdso_start, > + .vdso_code_end = vdso_end, > +}; > + > +static int vdso_mremap(const struct vm_special_mapping *sm, > + struct vm_area_struct *new_vma) > +{ > + current->mm->context.vdso = (void *)new_vma->vm_start; > + > + return 0; > +} > + > +static int __init __vdso_init(void) > { > unsigned int i; > + struct page **vdso_pagelist; > + unsigned long pfn; > > - vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT; > - vdso_pagelist = > - kcalloc(vdso_pages + VVAR_NR_PAGES, sizeof(struct page *), GFP_KERNEL); > - if (unlikely(vdso_pagelist == NULL)) { > - pr_err("vdso: pagelist allocation failed\n"); > - return -ENOMEM; > + if (memcmp(vdso_info.vdso_code_start, "\177ELF", 4)) { > + pr_err("vDSO is not a valid ELF object!\n"); > + return -EINVAL; > } > > - for (i = 0; i < vdso_pages; i++) { > - struct page *pg; > + vdso_info.vdso_pages = ( > + vdso_info.vdso_code_end - > + vdso_info.vdso_code_start) >> > + PAGE_SHIFT; > + > + vdso_pagelist = kcalloc(vdso_info.vdso_pages, > + sizeof(struct page *), > + GFP_KERNEL); > + if (vdso_pagelist == NULL) > + return -ENOMEM; > + > + /* Grab the vDSO code pages. */ > + pfn = sym_to_pfn(vdso_info.vdso_code_start); > + > + for (i = 0; i < vdso_info.vdso_pages; i++) > + vdso_pagelist[i] = pfn_to_page(pfn + i); > + > + vdso_info.cm->pages = vdso_pagelist; > + > + return 0; > +} > + > +#ifdef CONFIG_TIME_NS > +struct vdso_data *arch_get_vdso_data(void *vvar_page) > +{ > + return (struct vdso_data *)(vvar_page); > +} > + > +/* > + * The vvar mapping contains data for a specific time namespace, so when a task > + * changes namespace we must unmap its vvar data for the old namespace. > + * Subsequent faults will map in data for the new namespace. > + * > + * For more details see timens_setup_vdso_data(). > + */ > +int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) > +{ > + struct mm_struct *mm = task->mm; > + struct vm_area_struct *vma; > + > + mmap_read_lock(mm); > > - pg = virt_to_page(vdso_start + (i << PAGE_SHIFT)); > - vdso_pagelist[i] = pg; > + for (vma = mm->mmap; vma; vma = vma->vm_next) { > + unsigned long size = vma->vm_end - vma->vm_start; > + > + if (vma_is_special_mapping(vma, vdso_info.dm)) > + zap_page_range(vma, vma->vm_start, size); > } > - vdso_pagelist[i] = virt_to_page(vdso_data); > > + mmap_read_unlock(mm); > return 0; > } > + > +static struct page *find_timens_vvar_page(struct vm_area_struct *vma) > +{ > + if (likely(vma->vm_mm == current->mm)) > + return current->nsproxy->time_ns->vvar_page; > + > + /* > + * VM_PFNMAP | VM_IO protect .fault() handler from being called > + * through interfaces like /proc/$pid/mem or > + * process_vm_{readv,writev}() as long as there's no .access() > + * in special_mapping_vmops. > + * For more details check_vma_flags() and __access_remote_vm() > + */ > + WARN(1, "vvar_page accessed remotely"); > + > + return NULL; > +} > +#else > +static struct page *find_timens_vvar_page(struct vm_area_struct *vma) > +{ > + return NULL; > +} > +#endif > + > +static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, > + struct vm_area_struct *vma, struct vm_fault *vmf) > +{ > + struct page *timens_page = find_timens_vvar_page(vma); > + unsigned long pfn; > + > + switch (vmf->pgoff) { > + case VVAR_DATA_PAGE_OFFSET: > + if (timens_page) > + pfn = page_to_pfn(timens_page); > + else > + pfn = sym_to_pfn(vdso_data); > + break; > +#ifdef CONFIG_TIME_NS > + case VVAR_TIMENS_PAGE_OFFSET: > + /* > + * If a task belongs to a time namespace then a namespace > + * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and > + * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET > + * offset. > + * See also the comment near timens_setup_vdso_data(). > + */ > + if (!timens_page) > + return VM_FAULT_SIGBUS; > + pfn = sym_to_pfn(vdso_data); > + break; > +#endif /* CONFIG_TIME_NS */ > + default: > + return VM_FAULT_SIGBUS; > + } > + > + return vmf_insert_pfn(vma, vmf->address, pfn); > +} > + > +enum rv_vdso_map { > + RV_VDSO_MAP_VVAR, > + RV_VDSO_MAP_VDSO, > +}; > + > +static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = { > + [RV_VDSO_MAP_VVAR] = { > + .name = "[vvar]", > + .fault = vvar_fault, > + }, > + [RV_VDSO_MAP_VDSO] = { > + .name = "[vdso]", > + .mremap = vdso_mremap, > + }, > +}; > + > +static int __init vdso_init(void) > +{ > + vdso_info.dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR]; > + vdso_info.cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO]; > + > + return __vdso_init(); > +} > arch_initcall(vdso_init); > > -int arch_setup_additional_pages(struct linux_binprm *bprm, > - int uses_interp) > +static int __setup_additional_pages(struct mm_struct *mm, > + struct linux_binprm *bprm, > + int uses_interp) > { > - struct mm_struct *mm = current->mm; > - unsigned long vdso_base, vdso_len; > - int ret; > + unsigned long vdso_base, vdso_text_len, vdso_mapping_len; > + void *ret; > > BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES); > > - vdso_len = (vdso_pages + VVAR_NR_PAGES) << PAGE_SHIFT; > + vdso_text_len = vdso_info.vdso_pages << PAGE_SHIFT; > + /* Be sure to map the data page */ > + vdso_mapping_len = vdso_text_len + VVAR_SIZE; > > - if (mmap_write_lock_killable(mm)) > - return -EINTR; > - > - vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0); > + vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0); > if (IS_ERR_VALUE(vdso_base)) { > - ret = vdso_base; > - goto end; > + ret = ERR_PTR(vdso_base); > + goto up_fail; > } > > - mm->context.vdso = NULL; > - ret = install_special_mapping(mm, vdso_base, VVAR_SIZE, > - (VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]); > - if (unlikely(ret)) > - goto end; > + ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE, > + (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info.dm); > + if (IS_ERR(ret)) > + goto up_fail; > > + vdso_base += VVAR_SIZE; > + mm->context.vdso = (void *)vdso_base; > ret = > - install_special_mapping(mm, vdso_base + VVAR_SIZE, > - vdso_pages << PAGE_SHIFT, > + _install_special_mapping(mm, vdso_base, vdso_text_len, > (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC), > - vdso_pagelist); > + vdso_info.cm); > > - if (unlikely(ret)) > - goto end; > + if (IS_ERR(ret)) > + goto up_fail; > > - /* > - * Put vDSO base into mm struct. We need to do this before calling > - * install_special_mapping or the perf counter mmap tracking code > - * will fail to recognise it as a vDSO (since arch_vma_name fails). > - */ > - mm->context.vdso = (void *)vdso_base + VVAR_SIZE; > + return 0; > > -end: > - mmap_write_unlock(mm); > - return ret; > +up_fail: > + mm->context.vdso = NULL; > + return PTR_ERR(ret); > } > > -const char *arch_vma_name(struct vm_area_struct *vma) > +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) > { > - if (vma->vm_mm && (vma->vm_start == (long)vma->vm_mm->context.vdso)) > - return "[vdso]"; > - if (vma->vm_mm && (vma->vm_start == > - (long)vma->vm_mm->context.vdso - VVAR_SIZE)) > - return "[vdso_data]"; > - return NULL; > + struct mm_struct *mm = current->mm; > + int ret; > + > + if (mmap_write_lock_killable(mm)) > + return -EINTR; > + > + ret = __setup_additional_pages(mm, bprm, uses_interp); > + mmap_write_unlock(mm); > + > + return ret; > } > diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S > index e9111f700af0..01d94aae5bf5 100644 > --- a/arch/riscv/kernel/vdso/vdso.lds.S > +++ b/arch/riscv/kernel/vdso/vdso.lds.S > @@ -10,6 +10,9 @@ OUTPUT_ARCH(riscv) > SECTIONS > { > PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); > +#ifdef CONFIG_TIME_NS > + PROVIDE(_timens_data = _vdso_data + PAGE_SIZE); > +#endif > . = SIZEOF_HEADERS; > > .hash : { *(.hash) } :text > From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id A9C9FC433EF for ; Tue, 28 Sep 2021 02:36:33 +0000 (UTC) Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 5558460F6E for ; Tue, 28 Sep 2021 02:36:33 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org 5558460F6E Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=huawei.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=lists.infradead.org DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender:Content-Type: Content-Transfer-Encoding:List-Subscribe:List-Help:List-Post:List-Archive: List-Unsubscribe:List-Id:In-Reply-To:MIME-Version:Date:Message-ID:From:CC: References:To:Subject:Reply-To:Content-ID:Content-Description:Resent-Date: Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID:List-Owner; bh=Lf1dBA5DiLa6cehX2ZL8ELTnznUpSJ8s65X+H5DUiZw=; b=hRYI/BudrUmLXuvwO4TWwqU3B5 MGKBWlEcVjZOgGAEldMt0T0vSpoxMBmCi2zaFnU/tSK759JCeWuLC/Uk6aSUCpO6wmh+THvx/9F1Q bvFnH+BdoEmkInFwcWlzEDf/wGGcAumQ3gtd3l+ljPIMlNDpCguvoxv8Pe6xU3BzIwQ+nRNKRFPWO 91wVyJ7yPs+lOgd+1glSuRXCKfn8UylaaXqjbTmouxle+Lhe8TH7FrOTKf5noP/sXcGq9BLgaNyMv 6AP+q4x2C8vIz/r5PLz02ZezA9LB8rDoiwXySp1Zi0fPhA9zgwb0Vvd97R3fF6pA5sFMioWaHRHtS rLUreMbg==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.94.2 #2 (Red Hat Linux)) id 1mV2yZ-005JFc-1g; Tue, 28 Sep 2021 02:36:11 +0000 Received: from szxga01-in.huawei.com ([45.249.212.187]) by bombadil.infradead.org with esmtps (Exim 4.94.2 #2 (Red Hat Linux)) id 1mV2yD-005J7P-Rp for linux-riscv@lists.infradead.org; Tue, 28 Sep 2021 02:35:52 +0000 Received: from dggemv703-chm.china.huawei.com (unknown [172.30.72.56]) by szxga01-in.huawei.com (SkyGuard) with ESMTP id 4HJNr55ThSzWXtd; Tue, 28 Sep 2021 10:34:29 +0800 (CST) Received: from kwepemm600017.china.huawei.com (7.193.23.234) by dggemv703-chm.china.huawei.com (10.3.19.46) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2308.8; Tue, 28 Sep 2021 10:35:43 +0800 Received: from [10.174.179.234] (10.174.179.234) by kwepemm600017.china.huawei.com (7.193.23.234) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2308.8; Tue, 28 Sep 2021 10:35:43 +0800 Subject: Re: [PATCH -next] riscv/vdso: Add support for time namespaces To: Paul Walmsley , Palmer Dabbelt , Palmer Dabbelt , Albert Ou References: <20210901032025.2529454-1-tongtiangen@huawei.com> CC: , From: tongtiangen Message-ID: <6cdb42c0-9b80-1d09-f309-5691f0013a96@huawei.com> Date: Tue, 28 Sep 2021 10:35:42 +0800 User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:45.0) Gecko/20100101 Thunderbird/45.7.1 MIME-Version: 1.0 In-Reply-To: <20210901032025.2529454-1-tongtiangen@huawei.com> X-Originating-IP: [10.174.179.234] X-ClientProxiedBy: dggems705-chm.china.huawei.com (10.3.19.182) To kwepemm600017.china.huawei.com (7.193.23.234) X-CFilter-Loop: Reflected X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20210927_193550_316173_CADA702B X-CRM114-Status: GOOD ( 37.85 ) X-BeenThere: linux-riscv@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset="us-ascii"; Format="flowed" Sender: "linux-riscv" Errors-To: linux-riscv-bounces+linux-riscv=archiver.kernel.org@lists.infradead.org kindly ping. On 2021/9/1 11:20, Tong Tiangen wrote: > Implement generic vdso time namespace support which also enables time > namespaces for riscv. This is quite similar to what arm64 does. > > selftest/timens test result: > 1..10 > ok 1 Passed for CLOCK_BOOTTIME (syscall) > ok 2 Passed for CLOCK_BOOTTIME (vdso) > ok 3 # SKIP CLOCK_BOOTTIME_ALARM isn't supported > ok 4 # SKIP CLOCK_BOOTTIME_ALARM isn't supported > ok 5 Passed for CLOCK_MONOTONIC (syscall) > ok 6 Passed for CLOCK_MONOTONIC (vdso) > ok 7 Passed for CLOCK_MONOTONIC_COARSE (syscall) > ok 8 Passed for CLOCK_MONOTONIC_COARSE (vdso) > ok 9 Passed for CLOCK_MONOTONIC_RAW (syscall) > ok 10 Passed for CLOCK_MONOTONIC_RAW (vdso) > # Totals: pass:8 fail:0 xfail:0 xpass:0 skip:2 error:0 > > Signed-off-by: Tong Tiangen > --- > This patch is based on patchset: > https://lore.kernel.org/lkml/20210901024621.2528797-1-tongtiangen@huawei.com/ > > arch/riscv/Kconfig | 1 + > arch/riscv/include/asm/page.h | 2 + > arch/riscv/include/asm/vdso.h | 2 +- > arch/riscv/include/asm/vdso/gettimeofday.h | 7 + > arch/riscv/kernel/vdso.c | 250 ++++++++++++++++----- > arch/riscv/kernel/vdso/vdso.lds.S | 3 + > 6 files changed, 211 insertions(+), 54 deletions(-) > > diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig > index aac669a6c3d8..7b0eff8a7eef 100644 > --- a/arch/riscv/Kconfig > +++ b/arch/riscv/Kconfig > @@ -61,6 +61,7 @@ config RISCV > select GENERIC_SCHED_CLOCK > select GENERIC_SMP_IDLE_THREAD > select GENERIC_TIME_VSYSCALL if MMU && 64BIT > + select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO > select HANDLE_DOMAIN_IRQ > select HAVE_ARCH_AUDITSYSCALL > select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL > diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h > index 109c97e991a6..b3e5ff0125fe 100644 > --- a/arch/riscv/include/asm/page.h > +++ b/arch/riscv/include/asm/page.h > @@ -157,6 +157,8 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x); > #define page_to_bus(page) (page_to_phys(page)) > #define phys_to_page(paddr) (pfn_to_page(phys_to_pfn(paddr))) > > +#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) > + > #ifdef CONFIG_FLATMEM > #define pfn_valid(pfn) \ > (((pfn) >= ARCH_PFN_OFFSET) && (((pfn) - ARCH_PFN_OFFSET) < max_mapnr)) > diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h > index 34210b22ba91..bee9514104f7 100644 > --- a/arch/riscv/include/asm/vdso.h > +++ b/arch/riscv/include/asm/vdso.h > @@ -14,7 +14,7 @@ > */ > #ifdef CONFIG_MMU > > -#define __VVAR_PAGES 1 > +#define __VVAR_PAGES 2 > > #ifndef __ASSEMBLY__ > > diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h > index f839f16e0d2a..77d9c2f721c4 100644 > --- a/arch/riscv/include/asm/vdso/gettimeofday.h > +++ b/arch/riscv/include/asm/vdso/gettimeofday.h > @@ -76,6 +76,13 @@ static __always_inline const struct vdso_data *__arch_get_vdso_data(void) > return _vdso_data; > } > > +#ifdef CONFIG_TIME_NS > +static __always_inline > +const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) > +{ > + return _timens_data; > +} > +#endif > #endif /* !__ASSEMBLY__ */ > > #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ > diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c > index b70956d80408..a9436a65161a 100644 > --- a/arch/riscv/kernel/vdso.c > +++ b/arch/riscv/kernel/vdso.c > @@ -13,6 +13,7 @@ > #include > #include > #include > +#include > > #ifdef CONFIG_GENERIC_TIME_VSYSCALL > #include > @@ -25,14 +26,12 @@ extern char vdso_start[], vdso_end[]; > > enum vvar_pages { > VVAR_DATA_PAGE_OFFSET, > + VVAR_TIMENS_PAGE_OFFSET, > VVAR_NR_PAGES, > }; > > #define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) > > -static unsigned int vdso_pages __ro_after_init; > -static struct page **vdso_pagelist __ro_after_init; > - > /* > * The vDSO data page. > */ > @@ -42,83 +41,228 @@ static union { > } vdso_data_store __page_aligned_data; > struct vdso_data *vdso_data = &vdso_data_store.data; > > -static int __init vdso_init(void) > +struct __vdso_info { > + const char *name; > + const char *vdso_code_start; > + const char *vdso_code_end; > + unsigned long vdso_pages; > + /* Data Mapping */ > + struct vm_special_mapping *dm; > + /* Code Mapping */ > + struct vm_special_mapping *cm; > +}; > + > +static struct __vdso_info vdso_info __ro_after_init = { > + .name = "vdso", > + .vdso_code_start = vdso_start, > + .vdso_code_end = vdso_end, > +}; > + > +static int vdso_mremap(const struct vm_special_mapping *sm, > + struct vm_area_struct *new_vma) > +{ > + current->mm->context.vdso = (void *)new_vma->vm_start; > + > + return 0; > +} > + > +static int __init __vdso_init(void) > { > unsigned int i; > + struct page **vdso_pagelist; > + unsigned long pfn; > > - vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT; > - vdso_pagelist = > - kcalloc(vdso_pages + VVAR_NR_PAGES, sizeof(struct page *), GFP_KERNEL); > - if (unlikely(vdso_pagelist == NULL)) { > - pr_err("vdso: pagelist allocation failed\n"); > - return -ENOMEM; > + if (memcmp(vdso_info.vdso_code_start, "\177ELF", 4)) { > + pr_err("vDSO is not a valid ELF object!\n"); > + return -EINVAL; > } > > - for (i = 0; i < vdso_pages; i++) { > - struct page *pg; > + vdso_info.vdso_pages = ( > + vdso_info.vdso_code_end - > + vdso_info.vdso_code_start) >> > + PAGE_SHIFT; > + > + vdso_pagelist = kcalloc(vdso_info.vdso_pages, > + sizeof(struct page *), > + GFP_KERNEL); > + if (vdso_pagelist == NULL) > + return -ENOMEM; > + > + /* Grab the vDSO code pages. */ > + pfn = sym_to_pfn(vdso_info.vdso_code_start); > + > + for (i = 0; i < vdso_info.vdso_pages; i++) > + vdso_pagelist[i] = pfn_to_page(pfn + i); > + > + vdso_info.cm->pages = vdso_pagelist; > + > + return 0; > +} > + > +#ifdef CONFIG_TIME_NS > +struct vdso_data *arch_get_vdso_data(void *vvar_page) > +{ > + return (struct vdso_data *)(vvar_page); > +} > + > +/* > + * The vvar mapping contains data for a specific time namespace, so when a task > + * changes namespace we must unmap its vvar data for the old namespace. > + * Subsequent faults will map in data for the new namespace. > + * > + * For more details see timens_setup_vdso_data(). > + */ > +int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) > +{ > + struct mm_struct *mm = task->mm; > + struct vm_area_struct *vma; > + > + mmap_read_lock(mm); > > - pg = virt_to_page(vdso_start + (i << PAGE_SHIFT)); > - vdso_pagelist[i] = pg; > + for (vma = mm->mmap; vma; vma = vma->vm_next) { > + unsigned long size = vma->vm_end - vma->vm_start; > + > + if (vma_is_special_mapping(vma, vdso_info.dm)) > + zap_page_range(vma, vma->vm_start, size); > } > - vdso_pagelist[i] = virt_to_page(vdso_data); > > + mmap_read_unlock(mm); > return 0; > } > + > +static struct page *find_timens_vvar_page(struct vm_area_struct *vma) > +{ > + if (likely(vma->vm_mm == current->mm)) > + return current->nsproxy->time_ns->vvar_page; > + > + /* > + * VM_PFNMAP | VM_IO protect .fault() handler from being called > + * through interfaces like /proc/$pid/mem or > + * process_vm_{readv,writev}() as long as there's no .access() > + * in special_mapping_vmops. > + * For more details check_vma_flags() and __access_remote_vm() > + */ > + WARN(1, "vvar_page accessed remotely"); > + > + return NULL; > +} > +#else > +static struct page *find_timens_vvar_page(struct vm_area_struct *vma) > +{ > + return NULL; > +} > +#endif > + > +static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, > + struct vm_area_struct *vma, struct vm_fault *vmf) > +{ > + struct page *timens_page = find_timens_vvar_page(vma); > + unsigned long pfn; > + > + switch (vmf->pgoff) { > + case VVAR_DATA_PAGE_OFFSET: > + if (timens_page) > + pfn = page_to_pfn(timens_page); > + else > + pfn = sym_to_pfn(vdso_data); > + break; > +#ifdef CONFIG_TIME_NS > + case VVAR_TIMENS_PAGE_OFFSET: > + /* > + * If a task belongs to a time namespace then a namespace > + * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and > + * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET > + * offset. > + * See also the comment near timens_setup_vdso_data(). > + */ > + if (!timens_page) > + return VM_FAULT_SIGBUS; > + pfn = sym_to_pfn(vdso_data); > + break; > +#endif /* CONFIG_TIME_NS */ > + default: > + return VM_FAULT_SIGBUS; > + } > + > + return vmf_insert_pfn(vma, vmf->address, pfn); > +} > + > +enum rv_vdso_map { > + RV_VDSO_MAP_VVAR, > + RV_VDSO_MAP_VDSO, > +}; > + > +static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = { > + [RV_VDSO_MAP_VVAR] = { > + .name = "[vvar]", > + .fault = vvar_fault, > + }, > + [RV_VDSO_MAP_VDSO] = { > + .name = "[vdso]", > + .mremap = vdso_mremap, > + }, > +}; > + > +static int __init vdso_init(void) > +{ > + vdso_info.dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR]; > + vdso_info.cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO]; > + > + return __vdso_init(); > +} > arch_initcall(vdso_init); > > -int arch_setup_additional_pages(struct linux_binprm *bprm, > - int uses_interp) > +static int __setup_additional_pages(struct mm_struct *mm, > + struct linux_binprm *bprm, > + int uses_interp) > { > - struct mm_struct *mm = current->mm; > - unsigned long vdso_base, vdso_len; > - int ret; > + unsigned long vdso_base, vdso_text_len, vdso_mapping_len; > + void *ret; > > BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES); > > - vdso_len = (vdso_pages + VVAR_NR_PAGES) << PAGE_SHIFT; > + vdso_text_len = vdso_info.vdso_pages << PAGE_SHIFT; > + /* Be sure to map the data page */ > + vdso_mapping_len = vdso_text_len + VVAR_SIZE; > > - if (mmap_write_lock_killable(mm)) > - return -EINTR; > - > - vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0); > + vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0); > if (IS_ERR_VALUE(vdso_base)) { > - ret = vdso_base; > - goto end; > + ret = ERR_PTR(vdso_base); > + goto up_fail; > } > > - mm->context.vdso = NULL; > - ret = install_special_mapping(mm, vdso_base, VVAR_SIZE, > - (VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]); > - if (unlikely(ret)) > - goto end; > + ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE, > + (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info.dm); > + if (IS_ERR(ret)) > + goto up_fail; > > + vdso_base += VVAR_SIZE; > + mm->context.vdso = (void *)vdso_base; > ret = > - install_special_mapping(mm, vdso_base + VVAR_SIZE, > - vdso_pages << PAGE_SHIFT, > + _install_special_mapping(mm, vdso_base, vdso_text_len, > (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC), > - vdso_pagelist); > + vdso_info.cm); > > - if (unlikely(ret)) > - goto end; > + if (IS_ERR(ret)) > + goto up_fail; > > - /* > - * Put vDSO base into mm struct. We need to do this before calling > - * install_special_mapping or the perf counter mmap tracking code > - * will fail to recognise it as a vDSO (since arch_vma_name fails). > - */ > - mm->context.vdso = (void *)vdso_base + VVAR_SIZE; > + return 0; > > -end: > - mmap_write_unlock(mm); > - return ret; > +up_fail: > + mm->context.vdso = NULL; > + return PTR_ERR(ret); > } > > -const char *arch_vma_name(struct vm_area_struct *vma) > +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) > { > - if (vma->vm_mm && (vma->vm_start == (long)vma->vm_mm->context.vdso)) > - return "[vdso]"; > - if (vma->vm_mm && (vma->vm_start == > - (long)vma->vm_mm->context.vdso - VVAR_SIZE)) > - return "[vdso_data]"; > - return NULL; > + struct mm_struct *mm = current->mm; > + int ret; > + > + if (mmap_write_lock_killable(mm)) > + return -EINTR; > + > + ret = __setup_additional_pages(mm, bprm, uses_interp); > + mmap_write_unlock(mm); > + > + return ret; > } > diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S > index e9111f700af0..01d94aae5bf5 100644 > --- a/arch/riscv/kernel/vdso/vdso.lds.S > +++ b/arch/riscv/kernel/vdso/vdso.lds.S > @@ -10,6 +10,9 @@ OUTPUT_ARCH(riscv) > SECTIONS > { > PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); > +#ifdef CONFIG_TIME_NS > + PROVIDE(_timens_data = _vdso_data + PAGE_SIZE); > +#endif > . = SIZEOF_HEADERS; > > .hash : { *(.hash) } :text > _______________________________________________ linux-riscv mailing list linux-riscv@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-riscv