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 X-Spam-Level: X-Spam-Status: No, score=-0.9 required=3.0 tests=DKIM_SIGNED,DKIM_VALID, DKIM_VALID_AU,FREEMAIL_FORGED_FROMDOMAIN,FREEMAIL_FROM, HEADER_FROM_DIFFERENT_DOMAINS,MAILING_LIST_MULTI,SPF_PASS autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 2E922C433F4 for ; Mon, 27 Aug 2018 22:55:03 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id C4941208D5 for ; Mon, 27 Aug 2018 22:55:02 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="S3Xi/ysh" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org C4941208D5 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=gmail.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727452AbeH1Cnl (ORCPT ); Mon, 27 Aug 2018 22:43:41 -0400 Received: from mail-pl1-f194.google.com ([209.85.214.194]:42010 "EHLO mail-pl1-f194.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727058AbeH1Cnk (ORCPT ); Mon, 27 Aug 2018 22:43:40 -0400 Received: by mail-pl1-f194.google.com with SMTP id g23-v6so241757plq.9 for ; Mon, 27 Aug 2018 15:54:59 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=mime-version:subject:from:in-reply-to:date:cc :content-transfer-encoding:message-id:references:to; bh=Pb3qqGCFliSA0GCL+caugRMv493QhxPC8EU+HQD9rc8=; b=S3Xi/yshUQ+FGv/vzoFVLsYhQitPMp5iEdBB2jxUQFJo6qrLtOiHDddgosl5w0XkzD gFcYkVNICDzwBSrQUShaap1Fmc2yV4+8UPWQnuEOGN+WdcxLZ0BjiCTPAHxCGRrnj6eN a4Lb9stPJkqZUKU1N2wOe13raU7dpG982lnk7a4mWTlWKsO1+97VP9E7cEzAj7s0njJa VrCrCJapq6jTlwnqKBWH1R4KfrZjhHz9gXY3e7ieZ6oCjusmTaMsPSDXOCjfWFC37Lhd V95/baE6DLH4M7vddF8e8vhRuC2usfFnhL3LXY8nUq+doM2qF77sg4IAPH4nG41oUCBN Wfkw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:subject:from:in-reply-to:date:cc :content-transfer-encoding:message-id:references:to; bh=Pb3qqGCFliSA0GCL+caugRMv493QhxPC8EU+HQD9rc8=; b=uXt6jjfkNseOl070fA1bS3mdLE/Dmh7pmCPegEn7OQwZH+duQsbN9rW3RfpWuPCP7e k5I+sfN/hWxW7mIEAHc9dYNvW7HJlSWayirzeuENd7gGgFezDTGf1356ZFz/qBfW2WyK U+njDnp3h4pcO8UyqkxuIxcNXBXAormhFiQFbvEiH5/FDZ/ZFRCf2A6HX4dIvuXG1LVT zcjAd4TTGoh6tP+j+n1/U0wo7o8Ajz4fKDyxZoX2+CVfU2mB4PMatE/7nK0n+n78ffDo Mhef9EvvqIwuVHAU3fct1kQNleL6hpbiSB/aipV+d98bizYuClgjrqbQI8vpal2v4xOl Korw== X-Gm-Message-State: APzg51Bhkh38k3yf++TcwlgimTLLiQ2eITu/TrRkHfV9V2jeViqHmLon hEcbJBqTaf71fOg8xiHDfWI= X-Google-Smtp-Source: ANB0VdalBdCO31h5Jh7aO0LZZ/Qu7KqQjXev77/a182TRVgxmxHHMFp662pmZ/dpWNRH4EFqDwivVg== X-Received: by 2002:a17:902:925:: with SMTP id 34-v6mr14960947plm.307.1535410499056; Mon, 27 Aug 2018 15:54:59 -0700 (PDT) Received: from [10.33.114.204] ([66.170.99.1]) by smtp.gmail.com with ESMTPSA id h10-v6sm516704pfj.78.2018.08.27.15.54.57 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Mon, 27 Aug 2018 15:54:58 -0700 (PDT) Content-Type: text/plain; charset=utf-8 Mime-Version: 1.0 (Mac OS X Mail 11.5 \(3445.9.1\)) Subject: Re: TLB flushes on fixmap changes From: Nadav Amit In-Reply-To: Date: Mon, 27 Aug 2018 15:54:55 -0700 Cc: Masami Hiramatsu , Peter Zijlstra , Kees Cook , Linus Torvalds , Paolo Bonzini , Jiri Kosina , Will Deacon , Benjamin Herrenschmidt , Nick Piggin , the arch/x86 maintainers , Borislav Petkov , Rik van Riel , Jann Horn , Adin Scannell , Dave Hansen , Linux Kernel Mailing List , linux-mm , David Miller , Martin Schwidefsky , Michael Ellerman Content-Transfer-Encoding: quoted-printable Message-Id: <2998E63A-5663-4805-9DE7-829A5870AA6D@gmail.com> References: <20180824180438.GS24124@hirez.programming.kicks-ass.net> <56A9902F-44BE-4520-A17C-26650FCC3A11@gmail.com> <9A38D3F4-2F75-401D-8B4D-83A844C9061B@gmail.com> <8E0D8C66-6F21-4890-8984-B6B3082D4CC5@gmail.com> <20180826112341.f77a528763e297cbc36058fa@kernel.org> <20180826090958.GT24124@hirez.programming.kicks-ass.net> <20180827120305.01a6f26267c64610cadec5d8@kernel.org> <4BF82052-4738-441C-8763-26C85003F2C9@gmail.com> <20180827170511.6bafa15cbc102ae135366e86@kernel.org> <01DA0BDD-7504-4209-8A8F-20B27CF6A1C7@gmail.com> <0000D631-FDDF-4273-8F3C-714E6825E59B@gmail.com> <823D916E-4056-4A36-BDD8-0FB682A8DCAE@gmail.com> <08A6BCB2-66C2-47ED-AEB8-AA8F4D7DBD45@gmail.com> <4F72D40A-25A3-4C64-B8DD-56970CFDE61E@gmail.com> To: Andy Lutomirski X-Mailer: Apple Mail (2.3445.9.1) Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org at 3:32 PM, Andy Lutomirski wrote: > On Mon, Aug 27, 2018 at 2:55 PM, Nadav Amit = wrote: >> at 1:16 PM, Nadav Amit wrote: >>=20 >>> at 12:58 PM, Andy Lutomirski wrote: >>>=20 >>>> On Mon, Aug 27, 2018 at 12:43 PM, Nadav Amit = wrote: >>>>> at 12:10 PM, Nadav Amit wrote: >>>>>=20 >>>>>> at 11:58 AM, Andy Lutomirski wrote: >>>>>>=20 >>>>>>> On Mon, Aug 27, 2018 at 11:54 AM, Nadav Amit = wrote: >>>>>>>>> On Mon, Aug 27, 2018 at 10:34 AM, Nadav Amit = wrote: >>>>>>>>> What do you all think? >>>>>>>>=20 >>>>>>>> I agree in general. But I think that current->mm would need to = be loaded, as >>>>>>>> otherwise I am afraid it would break switch_mm_irqs_off(). >>>>>>>=20 >>>>>>> What breaks? >>>>>>=20 >>>>>> Actually nothing. I just saw the IBPB stuff regarding tsk, but it = should not >>>>>> matter. >>>>>=20 >>>>> So here is what I got. It certainly needs some cleanup, but it = boots. >>>>>=20 >>>>> Let me know how crappy you find it... >>>>>=20 >>>>>=20 >>>>> diff --git a/arch/x86/include/asm/mmu_context.h = b/arch/x86/include/asm/mmu_context.h >>>>> index bbc796eb0a3b..336779650a41 100644 >>>>> --- a/arch/x86/include/asm/mmu_context.h >>>>> +++ b/arch/x86/include/asm/mmu_context.h >>>>> @@ -343,4 +343,24 @@ static inline unsigned long = __get_current_cr3_fast(void) >>>>> return cr3; >>>>> } >>>>>=20 >>>>> +typedef struct { >>>>> + struct mm_struct *prev; >>>>> +} temporary_mm_state_t; >>>>> + >>>>> +static inline temporary_mm_state_t use_temporary_mm(struct = mm_struct *mm) >>>>> +{ >>>>> + temporary_mm_state_t state; >>>>> + >>>>> + lockdep_assert_irqs_disabled(); >>>>> + state.prev =3D this_cpu_read(cpu_tlbstate.loaded_mm); >>>>> + switch_mm_irqs_off(NULL, mm, current); >>>>> + return state; >>>>> +} >>>>> + >>>>> +static inline void unuse_temporary_mm(temporary_mm_state_t prev) >>>>> +{ >>>>> + lockdep_assert_irqs_disabled(); >>>>> + switch_mm_irqs_off(NULL, prev.prev, current); >>>>> +} >>>>> + >>>>> #endif /* _ASM_X86_MMU_CONTEXT_H */ >>>>> diff --git a/arch/x86/include/asm/pgtable.h = b/arch/x86/include/asm/pgtable.h >>>>> index 5715647fc4fe..ef62af9a0ef7 100644 >>>>> --- a/arch/x86/include/asm/pgtable.h >>>>> +++ b/arch/x86/include/asm/pgtable.h >>>>> @@ -976,6 +976,10 @@ static inline void __meminit = init_trampoline_default(void) >>>>> /* Default trampoline pgd value */ >>>>> trampoline_pgd_entry =3D = init_top_pgt[pgd_index(__PAGE_OFFSET)]; >>>>> } >>>>> + >>>>> +void __init patching_mm_init(void); >>>>> +#define patching_mm_init patching_mm_init >>>>> + >>>>> # ifdef CONFIG_RANDOMIZE_MEMORY >>>>> void __meminit init_trampoline(void); >>>>> # else >>>>> diff --git a/arch/x86/include/asm/pgtable_64_types.h = b/arch/x86/include/asm/pgtable_64_types.h >>>>> index 054765ab2da2..9f44262abde0 100644 >>>>> --- a/arch/x86/include/asm/pgtable_64_types.h >>>>> +++ b/arch/x86/include/asm/pgtable_64_types.h >>>>> @@ -116,6 +116,9 @@ extern unsigned int ptrs_per_p4d; >>>>> #define LDT_PGD_ENTRY (pgtable_l5_enabled() ? = LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4) >>>>> #define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) >>>>>=20 >>>>> +#define TEXT_POKE_PGD_ENTRY -5UL >>>>> +#define TEXT_POKE_ADDR (TEXT_POKE_PGD_ENTRY << = PGDIR_SHIFT) >>>>> + >>>>> #define __VMALLOC_BASE_L4 0xffffc90000000000UL >>>>> #define __VMALLOC_BASE_L5 0xffa0000000000000UL >>>>>=20 >>>>> diff --git a/arch/x86/include/asm/pgtable_types.h = b/arch/x86/include/asm/pgtable_types.h >>>>> index 99fff853c944..840c72ec8c4f 100644 >>>>> --- a/arch/x86/include/asm/pgtable_types.h >>>>> +++ b/arch/x86/include/asm/pgtable_types.h >>>>> @@ -505,6 +505,9 @@ pgprot_t phys_mem_access_prot(struct file = *file, unsigned long pfn, >>>>> /* Install a pte for a particular vaddr in kernel space. */ >>>>> void set_pte_vaddr(unsigned long vaddr, pte_t pte); >>>>>=20 >>>>> +struct mm_struct; >>>>> +void set_mm_pte_vaddr(struct mm_struct *mm, unsigned long vaddr, = pte_t pte); >>>>> + >>>>> #ifdef CONFIG_X86_32 >>>>> extern void native_pagetable_init(void); >>>>> #else >>>>> diff --git a/arch/x86/include/asm/text-patching.h = b/arch/x86/include/asm/text-patching.h >>>>> index 2ecd34e2d46c..cb364ea5b19d 100644 >>>>> --- a/arch/x86/include/asm/text-patching.h >>>>> +++ b/arch/x86/include/asm/text-patching.h >>>>> @@ -38,4 +38,6 @@ extern void *text_poke(void *addr, const void = *opcode, size_t len); >>>>> extern int poke_int3_handler(struct pt_regs *regs); >>>>> extern void *text_poke_bp(void *addr, const void *opcode, size_t = len, void *handler); >>>>>=20 >>>>> +extern struct mm_struct *patching_mm; >>>>> + >>>>> #endif /* _ASM_X86_TEXT_PATCHING_H */ >>>>> diff --git a/arch/x86/kernel/alternative.c = b/arch/x86/kernel/alternative.c >>>>> index a481763a3776..fd8a950b0d62 100644 >>>>> --- a/arch/x86/kernel/alternative.c >>>>> +++ b/arch/x86/kernel/alternative.c >>>>> @@ -11,6 +11,7 @@ >>>>> #include >>>>> #include >>>>> #include >>>>> +#include >>>>> #include >>>>> #include >>>>> #include >>>>> @@ -701,8 +702,36 @@ void *text_poke(void *addr, const void = *opcode, size_t len) >>>>> WARN_ON(!PageReserved(pages[0])); >>>>> pages[1] =3D virt_to_page(addr + PAGE_SIZE); >>>>> } >>>>> - BUG_ON(!pages[0]); >>>>> + >>>>> local_irq_save(flags); >>>>> + BUG_ON(!pages[0]); >>>>> + >>>>> + /* >>>>> + * During initial boot, it is hard to initialize = patching_mm due to >>>>> + * dependencies in boot order. >>>>> + */ >>>>> + if (patching_mm) { >>>>> + pte_t pte; >>>>> + temporary_mm_state_t prev; >>>>> + >>>>> + prev =3D use_temporary_mm(patching_mm); >>>>> + pte =3D mk_pte(pages[0], PAGE_KERNEL); >>>>> + set_mm_pte_vaddr(patching_mm, TEXT_POKE_ADDR, = pte); >>>>> + pte =3D mk_pte(pages[1], PAGE_KERNEL); >>>>> + set_mm_pte_vaddr(patching_mm, TEXT_POKE_ADDR + = PAGE_SIZE, pte); >>>>> + >>>>> + memcpy((void *)(TEXT_POKE_ADDR | ((unsigned = long)addr & ~PAGE_MASK)), >>>>> + opcode, len); >>>>> + >>>>> + set_mm_pte_vaddr(patching_mm, TEXT_POKE_ADDR, = __pte(0)); >>>>> + set_mm_pte_vaddr(patching_mm, TEXT_POKE_ADDR + = PAGE_SIZE, __pte(0)); >>>>> + local_flush_tlb(); >>>>=20 >>>> Hmm. This is stuff busted on SMP, and it's IMO more complicated = than >>>> needed. How about getting rid of all the weird TLB flushing stuff = and >>>> instead putting the mapping at vaddr - __START_KERNEL_map or = whatever >>>> it is? You *might* need to flush_tlb_mm_range() on module unload, = but >>>> that's it. >>>=20 >>> I don=E2=80=99t see what=E2=80=99s wrong in SMP, since this entire = piece of code should be >>> running under text_mutex. >>>=20 >>> I don=E2=80=99t quite understand your proposal. I really don=E2=80=99t= want to have any >>> chance in which the page-tables for the poked address is not = preallocated. >>>=20 >>> It is more complicated than needed, and there are redundant TLB = flushes. The >>> reason I preferred to do it this way, is in order not to use other = functions >>> that take locks during the software page-walk and not to duplicate = existing >>> code. Yet, duplication might be the way to go. >>>=20 >>>>> + sync_core(); >>>>=20 >>>> I can't think of any case where sync_core() is needed. The mm = switch >>>> serializes. >>>=20 >>> Good point! >>>=20 >>>> Also, is there any circumstance in which any of this is used before = at >>>> least jump table init? All the early stuff is text_poke_early(), >>>> right? >>>=20 >>> Not before jump_label_init. However, I did not manage to get rid of = the two >>> code-patches in text_poke(), since text_poke is used relatively = early by >>> x86_late_time_init(), and at this stage kmem_cache_alloc() - which = is needed >>> to duplicate init_mm - still fails. >>=20 >> Another correction: the populate_extra_pte() is not needed. >>=20 >> Anyhow, if you want to do this whole thing differently, I obviously = will not >> object, but I think it will end up more complicated. >>=20 >> I think I finally understood your comment about "vaddr - >> __START_KERNEL_map=E2=80=9D. I did something like that before, and it = is not >> super-simple. You need not only to conditionally flush the TLB, but = also >> to synchronize the PUD/PMD on changes. Don=E2=80=99t forget that = module memory >> is installed even when BPF programs are installed. >>=20 >> Let me know if you want me to submit cleaner patches or you want to = carry on >> yourself. >=20 > I think your approach is a good start and should be good enough (with > cleanups) as a fix for the bug. But I think your code has the same > bug that we have now! You're reusing the same address on multiple > CPUs without flushing. You can easily fix it by forcing a flush > before loading the mm, which should be as simple as adding > flush_tlb_mm() before you load the mm. (It won't actually flush > anything by itself, since the mm isn't loaded, but it will update the > bookkeeping so that switch_mm_irqs_off() flushes the mm.) What am I missing? We have a lock (text_mutex) which prevents the use of the new page-table hierarchy on multiple CPUs. In addition we have __set_pte_vaddr() which = does a local TLB flush before the lock is released and before IRQs are = enabled. So how can the PTE be cached on multiple CPUs? Yes, __set_pte_vaddr() is ugly and flushes too much. I=E2=80=99ll try to = remove some redundant TLB flushes, but these flushes are already there. > Also, please at least get rid of TEXT_POKE_ADDR. If you don't want to > do the vaddr - __START_KERNEL_map thing, then at least pick an address > in the low half of the address space such as 0 :) Ideally you'd only > use this thing late enough that you could even use the normal > insert_pfn (or similar) API for it, but that doesn't really matter. Perhaps the vaddr - __START_KERNEL_map actually makes sense. I was misunderstanding it (again) before, thinking you want me to use vaddr = (and not the delta). I=E2=80=99ll give it a try. Thanks, Nadav