From: Thomas Gleixner <tglx@linutronix.de> To: Dave Hansen <dave.hansen@linux.intel.com> Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org, moritz.lipp@iaik.tugraz.at, daniel.gruss@iaik.tugraz.at, michael.schwarz@iaik.tugraz.at, luto@kernel.org, torvalds@linux-foundation.org, keescook@google.com, hughd@google.com, x86@kernel.org Subject: Re: [PATCH 06/23] x86, kaiser: introduce user-mapped percpu areas Date: Wed, 1 Nov 2017 22:47:54 +0100 (CET) [thread overview] Message-ID: <alpine.DEB.2.20.1711012231250.1942@nanos> (raw) In-Reply-To: <20171031223158.A60B4068@viggo.jf.intel.com> On Tue, 31 Oct 2017, Dave Hansen wrote: > > These patches are based on work from a team at Graz University of > Technology posted here: https://github.com/IAIK/KAISER > > The KAISER approach keeps two copies of the page tables: one for running > in the kernel and one for running userspace. But, there are a few > structures that are needed for switching in and out of the kernel and > a good subset of *those* are per-cpu data. > > This patch creates a new kind of per-cpu data that is mapped and can be > used no matter which copy of the page tables we are using. Please split out the percpu-defs.h change into a seperate patch. > -DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page); > +DECLARE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(struct gdt_page, gdt_page); Ok. > /* Provide the original GDT */ > static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu) > diff -puN arch/x86/include/asm/hw_irq.h~kaiser-prep-user-mapped-percpu arch/x86/include/asm/hw_irq.h > --- a/arch/x86/include/asm/hw_irq.h~kaiser-prep-user-mapped-percpu 2017-10-31 15:03:51.048146366 -0700 > +++ b/arch/x86/include/asm/hw_irq.h 2017-10-31 15:03:51.066147217 -0700 > @@ -160,7 +160,7 @@ extern char irq_entries_start[]; > #define VECTOR_RETRIGGERED ((void *)~0UL) > > typedef struct irq_desc* vector_irq_t[NR_VECTORS]; > -DECLARE_PER_CPU(vector_irq_t, vector_irq); > +DECLARE_PER_CPU_USER_MAPPED(vector_irq_t, vector_irq); Why? The vector_irq array has nothing to do with user space. It's a software handled storage which is used in the irq dispatcher way after the exception entry happened. I think you confused that with the IDT, which is missing here. > -DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); > +DECLARE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct tss_struct, cpu_tss); Ok. > -DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { > +DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(struct gdt_page, gdt_page) = { .gdt = { Ok. > -static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks > +DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(char, exception_stacks > [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); Hmm. I don't think that's a good idea. We discussed that in Prague with Andy and the Peters and came to the conclusion that we want a stub stack in the user mapping and switch to the kernel stacks in software after switching back to the kernel mappings. Andys 'Pile o' entry...' series paves the way to that already. So can we please put kaiser on top of those and do it proper right away? > -DEFINE_PER_CPU(vector_irq_t, vector_irq) = { > +DEFINE_PER_CPU_USER_MAPPED(vector_irq_t, vector_irq) = { > [0 ... NR_VECTORS - 1] = VECTOR_UNUSED, > }; See above. Thanks, tglx
WARNING: multiple messages have this Message-ID (diff)
From: Thomas Gleixner <tglx@linutronix.de> To: Dave Hansen <dave.hansen@linux.intel.com> Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org, moritz.lipp@iaik.tugraz.at, daniel.gruss@iaik.tugraz.at, michael.schwarz@iaik.tugraz.at, luto@kernel.org, torvalds@linux-foundation.org, keescook@google.com, hughd@google.com, x86@kernel.org Subject: Re: [PATCH 06/23] x86, kaiser: introduce user-mapped percpu areas Date: Wed, 1 Nov 2017 22:47:54 +0100 (CET) [thread overview] Message-ID: <alpine.DEB.2.20.1711012231250.1942@nanos> (raw) In-Reply-To: <20171031223158.A60B4068@viggo.jf.intel.com> On Tue, 31 Oct 2017, Dave Hansen wrote: > > These patches are based on work from a team at Graz University of > Technology posted here: https://github.com/IAIK/KAISER > > The KAISER approach keeps two copies of the page tables: one for running > in the kernel and one for running userspace. But, there are a few > structures that are needed for switching in and out of the kernel and > a good subset of *those* are per-cpu data. > > This patch creates a new kind of per-cpu data that is mapped and can be > used no matter which copy of the page tables we are using. Please split out the percpu-defs.h change into a seperate patch. > -DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page); > +DECLARE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(struct gdt_page, gdt_page); Ok. > /* Provide the original GDT */ > static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu) > diff -puN arch/x86/include/asm/hw_irq.h~kaiser-prep-user-mapped-percpu arch/x86/include/asm/hw_irq.h > --- a/arch/x86/include/asm/hw_irq.h~kaiser-prep-user-mapped-percpu 2017-10-31 15:03:51.048146366 -0700 > +++ b/arch/x86/include/asm/hw_irq.h 2017-10-31 15:03:51.066147217 -0700 > @@ -160,7 +160,7 @@ extern char irq_entries_start[]; > #define VECTOR_RETRIGGERED ((void *)~0UL) > > typedef struct irq_desc* vector_irq_t[NR_VECTORS]; > -DECLARE_PER_CPU(vector_irq_t, vector_irq); > +DECLARE_PER_CPU_USER_MAPPED(vector_irq_t, vector_irq); Why? The vector_irq array has nothing to do with user space. It's a software handled storage which is used in the irq dispatcher way after the exception entry happened. I think you confused that with the IDT, which is missing here. > -DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); > +DECLARE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct tss_struct, cpu_tss); Ok. > -DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { > +DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(struct gdt_page, gdt_page) = { .gdt = { Ok. > -static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks > +DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(char, exception_stacks > [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); Hmm. I don't think that's a good idea. We discussed that in Prague with Andy and the Peters and came to the conclusion that we want a stub stack in the user mapping and switch to the kernel stacks in software after switching back to the kernel mappings. Andys 'Pile o' entry...' series paves the way to that already. So can we please put kaiser on top of those and do it proper right away? > -DEFINE_PER_CPU(vector_irq_t, vector_irq) = { > +DEFINE_PER_CPU_USER_MAPPED(vector_irq_t, vector_irq) = { > [0 ... NR_VECTORS - 1] = VECTOR_UNUSED, > }; See above. Thanks, tglx -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2017-11-01 21:48 UTC|newest] Thread overview: 204+ messages / expand[flat|nested] mbox.gz Atom feed top 2017-10-31 22:31 [PATCH 00/23] KAISER: unmap most of the kernel from userspace page tables Dave Hansen 2017-10-31 22:31 ` Dave Hansen 2017-10-31 22:31 ` [PATCH 01/23] x86, kaiser: prepare assembly for entry/exit CR3 switching Dave Hansen 2017-10-31 22:31 ` Dave Hansen 2017-11-01 0:43 ` Brian Gerst 2017-11-01 0:43 ` Brian Gerst 2017-11-01 1:08 ` Dave Hansen 2017-11-01 1:08 ` Dave Hansen 2017-11-01 18:18 ` Borislav Petkov 2017-11-01 18:18 ` Borislav Petkov 2017-11-01 18:27 ` Dave Hansen 2017-11-01 18:27 ` Dave Hansen 2017-11-01 20:42 ` Borislav Petkov 2017-11-01 20:42 ` Borislav Petkov 2017-11-01 21:01 ` Thomas Gleixner 2017-11-01 21:01 ` Thomas Gleixner 2017-11-01 22:58 ` Dave Hansen 2017-11-01 22:58 ` Dave Hansen 2017-10-31 22:31 ` [PATCH 02/23] x86, kaiser: do not set _PAGE_USER for init_mm page tables Dave Hansen 2017-10-31 22:31 ` Dave Hansen 2017-11-01 21:11 ` Thomas Gleixner 2017-11-01 21:11 ` Thomas Gleixner 2017-11-01 21:24 ` Andy Lutomirski 2017-11-01 21:24 ` Andy Lutomirski 2017-11-01 21:28 ` Thomas Gleixner 2017-11-01 21:28 ` Thomas Gleixner 2017-11-01 21:52 ` Dave Hansen 2017-11-01 21:52 ` Dave Hansen 2017-11-01 22:11 ` Thomas Gleixner 2017-11-01 22:11 ` Thomas Gleixner 2017-11-01 22:12 ` Linus Torvalds 2017-11-01 22:12 ` Linus Torvalds 2017-11-01 22:20 ` Thomas Gleixner 2017-11-01 22:20 ` Thomas Gleixner 2017-11-01 22:45 ` Kees Cook 2017-11-01 22:45 ` Kees Cook 2017-11-02 7:10 ` Andy Lutomirski 2017-11-02 7:10 ` Andy Lutomirski 2017-11-02 11:33 ` Thomas Gleixner 2017-11-02 11:33 ` Thomas Gleixner 2017-11-02 11:59 ` Andy Lutomirski 2017-11-02 11:59 ` Andy Lutomirski 2017-11-02 12:56 ` Thomas Gleixner 2017-11-02 12:56 ` Thomas Gleixner 2017-11-02 16:38 ` Dave Hansen 2017-11-02 16:38 ` Dave Hansen 2017-11-02 18:19 ` Andy Lutomirski 2017-11-02 18:19 ` Andy Lutomirski 2017-11-02 18:24 ` Thomas Gleixner 2017-11-02 18:24 ` Thomas Gleixner 2017-11-02 18:24 ` Linus Torvalds 2017-11-02 18:24 ` Linus Torvalds 2017-11-02 18:40 ` Thomas Gleixner 2017-11-02 18:40 ` Thomas Gleixner 2017-11-02 18:57 ` Linus Torvalds 2017-11-02 18:57 ` Linus Torvalds 2017-11-02 21:41 ` Thomas Gleixner 2017-11-02 21:41 ` Thomas Gleixner 2017-11-02 7:07 ` Andy Lutomirski 2017-11-02 7:07 ` Andy Lutomirski 2017-11-02 11:21 ` Thomas Gleixner 2017-11-02 11:21 ` Thomas Gleixner 2017-10-31 22:31 ` [PATCH 03/23] x86, kaiser: disable global pages Dave Hansen 2017-10-31 22:31 ` Dave Hansen 2017-11-01 21:18 ` Thomas Gleixner 2017-11-01 21:18 ` Thomas Gleixner 2017-11-01 22:12 ` Dave Hansen 2017-11-01 22:12 ` Dave Hansen 2017-11-01 22:28 ` Thomas Gleixner 2017-11-01 22:28 ` Thomas Gleixner 2017-10-31 22:31 ` [PATCH 04/23] x86, tlb: make CR4-based TLB flushes more robust Dave Hansen 2017-10-31 22:31 ` Dave Hansen 2017-11-01 8:01 ` Andy Lutomirski 2017-11-01 8:01 ` Andy Lutomirski 2017-11-01 10:11 ` Kirill A. Shutemov 2017-11-01 10:11 ` Kirill A. Shutemov 2017-11-01 10:38 ` Andy Lutomirski 2017-11-01 10:38 ` Andy Lutomirski 2017-11-01 10:56 ` Kirill A. Shutemov 2017-11-01 10:56 ` Kirill A. Shutemov 2017-11-01 11:18 ` Andy Lutomirski 2017-11-01 11:18 ` Andy Lutomirski 2017-11-01 22:21 ` Dave Hansen 2017-11-01 22:21 ` Dave Hansen 2017-11-01 21:25 ` Thomas Gleixner 2017-11-01 21:25 ` Thomas Gleixner 2017-11-01 22:24 ` Dave Hansen 2017-11-01 22:24 ` Dave Hansen 2017-11-01 22:30 ` Thomas Gleixner 2017-11-01 22:30 ` Thomas Gleixner 2017-10-31 22:31 ` [PATCH 05/23] x86, mm: document X86_CR4_PGE toggling behavior Dave Hansen 2017-10-31 22:31 ` Dave Hansen 2017-10-31 23:31 ` Kees Cook 2017-10-31 23:31 ` Kees Cook 2017-10-31 22:31 ` [PATCH 06/23] x86, kaiser: introduce user-mapped percpu areas Dave Hansen 2017-10-31 22:31 ` Dave Hansen 2017-11-01 21:47 ` Thomas Gleixner [this message] 2017-11-01 21:47 ` Thomas Gleixner 2017-10-31 22:31 ` [PATCH 07/23] x86, kaiser: unmap kernel from userspace page tables (core patch) Dave Hansen 2017-10-31 22:31 ` Dave Hansen 2017-10-31 22:32 ` [PATCH 08/23] x86, kaiser: only populate shadow page tables for userspace Dave Hansen 2017-10-31 22:32 ` Dave Hansen 2017-10-31 23:35 ` Kees Cook 2017-10-31 23:35 ` Kees Cook 2017-10-31 22:32 ` [PATCH 09/23] x86, kaiser: allow NX to be set in p4d/pgd Dave Hansen 2017-10-31 22:32 ` Dave Hansen 2017-10-31 22:32 ` [PATCH 10/23] x86, kaiser: make sure static PGDs are 8k in size Dave Hansen 2017-10-31 22:32 ` Dave Hansen 2017-10-31 22:32 ` [PATCH 11/23] x86, kaiser: map GDT into user page tables Dave Hansen 2017-10-31 22:32 ` Dave Hansen 2017-10-31 22:32 ` [PATCH 12/23] x86, kaiser: map dynamically-allocated LDTs Dave Hansen 2017-10-31 22:32 ` Dave Hansen 2017-11-01 8:00 ` Andy Lutomirski 2017-11-01 8:00 ` Andy Lutomirski 2017-11-01 8:06 ` Ingo Molnar 2017-11-01 8:06 ` Ingo Molnar 2017-10-31 22:32 ` [PATCH 13/23] x86, kaiser: map espfix structures Dave Hansen 2017-10-31 22:32 ` Dave Hansen 2017-10-31 22:32 ` [PATCH 14/23] x86, kaiser: map entry stack variables Dave Hansen 2017-10-31 22:32 ` Dave Hansen 2017-10-31 22:32 ` [PATCH 15/23] x86, kaiser: map trace interrupt entry Dave Hansen 2017-10-31 22:32 ` Dave Hansen 2017-10-31 22:32 ` [PATCH 16/23] x86, kaiser: map debug IDT tables Dave Hansen 2017-10-31 22:32 ` Dave Hansen 2017-10-31 22:32 ` [PATCH 17/23] x86, kaiser: map virtually-addressed performance monitoring buffers Dave Hansen 2017-10-31 22:32 ` Dave Hansen 2017-10-31 22:32 ` [PATCH 18/23] x86, mm: Move CR3 construction functions Dave Hansen 2017-10-31 22:32 ` Dave Hansen 2017-10-31 22:32 ` [PATCH 19/23] x86, mm: remove hard-coded ASID limit checks Dave Hansen 2017-10-31 22:32 ` Dave Hansen 2017-10-31 22:32 ` [PATCH 20/23] x86, mm: put mmu-to-h/w ASID translation in one place Dave Hansen 2017-10-31 22:32 ` Dave Hansen 2017-10-31 22:32 ` [PATCH 21/23] x86, pcid, kaiser: allow flushing for future ASID switches Dave Hansen 2017-10-31 22:32 ` Dave Hansen 2017-11-01 8:03 ` Andy Lutomirski 2017-11-01 8:03 ` Andy Lutomirski 2017-11-01 14:17 ` Dave Hansen 2017-11-01 14:17 ` Dave Hansen 2017-11-01 20:31 ` Andy Lutomirski 2017-11-01 20:31 ` Andy Lutomirski 2017-11-01 20:59 ` Dave Hansen 2017-11-01 20:59 ` Dave Hansen 2017-11-01 21:04 ` Andy Lutomirski 2017-11-01 21:04 ` Andy Lutomirski 2017-11-01 21:06 ` Dave Hansen 2017-11-01 21:06 ` Dave Hansen 2017-10-31 22:32 ` [PATCH 22/23] x86, kaiser: use PCID feature to make user and kernel switches faster Dave Hansen 2017-10-31 22:32 ` Dave Hansen 2017-10-31 22:32 ` [PATCH 23/23] x86, kaiser: add Kconfig Dave Hansen 2017-10-31 22:32 ` Dave Hansen 2017-10-31 23:59 ` Kees Cook 2017-10-31 23:59 ` Kees Cook 2017-11-01 9:07 ` Borislav Petkov 2017-11-01 9:07 ` Borislav Petkov 2017-10-31 23:27 ` [PATCH 00/23] KAISER: unmap most of the kernel from userspace page tables Linus Torvalds 2017-10-31 23:27 ` Linus Torvalds 2017-10-31 23:44 ` Dave Hansen 2017-10-31 23:44 ` Dave Hansen 2017-11-01 0:21 ` Dave Hansen 2017-11-01 0:21 ` Dave Hansen 2017-11-01 7:59 ` Andy Lutomirski 2017-11-01 7:59 ` Andy Lutomirski 2017-11-01 16:08 ` Linus Torvalds 2017-11-01 16:08 ` Linus Torvalds 2017-11-01 17:31 ` Dave Hansen 2017-11-01 17:58 ` Randy Dunlap 2017-11-01 17:58 ` Randy Dunlap 2017-11-01 18:27 ` Linus Torvalds 2017-11-01 18:27 ` Linus Torvalds 2017-11-01 18:46 ` Dave Hansen 2017-11-01 18:46 ` Dave Hansen 2017-11-01 19:05 ` Linus Torvalds 2017-11-01 19:05 ` Linus Torvalds 2017-11-01 20:33 ` Andy Lutomirski 2017-11-01 20:33 ` Andy Lutomirski 2017-11-02 7:32 ` Andy Lutomirski 2017-11-02 7:32 ` Andy Lutomirski 2017-11-02 7:54 ` Andy Lutomirski 2017-11-02 7:54 ` Andy Lutomirski 2017-11-01 15:53 ` Dave Hansen 2017-11-01 15:53 ` Dave Hansen 2017-11-01 8:54 ` Ingo Molnar 2017-11-01 8:54 ` Ingo Molnar 2017-11-01 14:09 ` Thomas Gleixner 2017-11-01 14:09 ` Thomas Gleixner 2017-11-01 22:14 ` Dave Hansen 2017-11-01 22:14 ` Dave Hansen 2017-11-01 22:28 ` Linus Torvalds 2017-11-01 22:28 ` Linus Torvalds 2017-11-02 8:03 ` Peter Zijlstra 2017-11-02 8:03 ` Peter Zijlstra 2017-11-03 11:07 ` Kirill A. Shutemov 2017-11-03 11:07 ` Kirill A. Shutemov 2017-11-02 19:01 ` Will Deacon 2017-11-02 19:01 ` Will Deacon 2017-11-02 19:01 ` Will Deacon 2017-11-02 19:38 ` Dave Hansen 2017-11-02 19:38 ` Dave Hansen 2017-11-02 19:38 ` Dave Hansen 2017-11-03 13:41 ` Will Deacon 2017-11-03 13:41 ` Will Deacon 2017-11-03 13:41 ` Will Deacon 2017-11-22 16:19 ` Pavel Machek 2017-11-23 10:47 ` Pavel Machek
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=alpine.DEB.2.20.1711012231250.1942@nanos \ --to=tglx@linutronix.de \ --cc=daniel.gruss@iaik.tugraz.at \ --cc=dave.hansen@linux.intel.com \ --cc=hughd@google.com \ --cc=keescook@google.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=luto@kernel.org \ --cc=michael.schwarz@iaik.tugraz.at \ --cc=moritz.lipp@iaik.tugraz.at \ --cc=torvalds@linux-foundation.org \ --cc=x86@kernel.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.