mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Thomas Gleixner <tglx@linutronix.de>
To: Andy Lutomirski <luto@kernel.org>
Cc: X86 ML <x86@kernel.org>, Borislav Petkov <bpetkov@suse.de>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Brian Gerst <brgerst@gmail.com>,
	Dave Hansen <dave.hansen@intel.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Josh Poimboeuf <jpoimboe@redhat.com>
Subject: Re: [PATCH v2 13/18] x86/asm/64: Use a percpu trampoline stack for IDT entries
Date: Fri, 24 Nov 2017 00:44:34 +0100 (CET)	[thread overview]
Message-ID: <alpine.DEB.2.20.1711232239200.2364@nanos> (raw)
In-Reply-To: <a45e88dff7dfc1a496e6ecc6686af6a236640497.1511325444.git.luto@kernel.org>

On Tue, 21 Nov 2017, Andy Lutomirski wrote:
> The asm isn't exactly beautiful,

Delightful euphemism :)

> but I think that fully refactoring
> it can wait.

> @@ -560,6 +560,14 @@ END(irq_entries_start)
>  	.macro interrupt func
>  	cld
>  	ALLOC_PT_GPREGS_ON_STACK
> +
> +	testb	$3, CS(%rsp)
> +	jz	1f
> +	SWAPGS
> +	call	switch_to_thread_stack
> +	SWAPGS

I'm surely missing something subtle, but the register saving does really
not care on which GS it is. This swapgs orgy looks odd.

> +1:
> +
>  	SAVE_C_REGS
>  	SAVE_EXTRA_REGS
>  	ENCODE_FRAME_POINTER
> @@ -827,6 +835,33 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
>   */
>  #define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8)
>  
> +/*
> + * Switch to the thread stack.  This is called with the IRET frame and
> + * orig_ax in pt_regs and the rest of pt_regs allocated, but with all GPRs
> + * in the CPU registers.

That took several attempts to grok why you left ALLOC_PT_GPRES_ON_STACK in
place in the interrupts macro above.

In theory it would be sufficient to push %rdi on the entry stack and
operate from there, but it spares only the 'addq %rsp'. Not worth the
trouble of dealing with different register offsets.

A comment to that effect would be useful if you look at that 3 month from
now.

> + */
> +ENTRY(switch_to_thread_stack)
> +	UNWIND_HINT_IRET_REGS offset=17*8
> +
> +	movq	%rdi, RDI+8(%rsp)
> +	movq	%rsp, %rdi
> +	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
> +	UNWIND_HINT_IRET_REGS offset=17*8 base=%rdi
> +
> +	pushq	SS+8(%rdi)		/* regs->ss */
> +	pushq	RSP+8(%rdi)		/* regs->rsp */
> +	pushq	EFLAGS+8(%rdi)		/* regs->eflags */
> +	pushq	CS+8(%rdi)		/* regs->cs */
> +	pushq	RIP+8(%rdi)		/* regs->ip */
> +	pushq	ORIG_RAX+8(%rdi)	/* regs->orig_ax */
> +	ALLOC_PT_GPREGS_ON_STACK	/* allocate the rest of regs */
> +	pushq	(%rdi)			/* return address */
> +
> +	movq	RDI+8(%rdi), %rdi
> +	UNWIND_HINT_IRET_REGS offset=17*8
> +	ret
> +END(switch_to_thread_stack)

Thanks,

	tglx

  reply	other threads:[~2017-11-23 23:44 UTC|newest]

Thread overview: 64+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-11-22  4:43 [PATCH v2 00/18] Entry stack switching Andy Lutomirski
2017-11-22  4:43 ` [PATCH v2 01/18] x86/entry/64: Fix entry_SYSCALL_64_after_hwframe IRQ tracing Andy Lutomirski
2017-11-22  5:35   ` Ingo Molnar
2017-11-22  7:45   ` [tip:x86/urgent] x86/entry/64: Fix entry_SYSCALL_64_after_hwframe() " tip-bot for Andy Lutomirski
2017-11-22  4:43 ` [PATCH v2 02/18] x86/asm/64: Allocate and enable the SYSENTER stack Andy Lutomirski
2017-11-22  4:43 ` [PATCH v2 03/18] x86/dumpstack: Add get_stack_info() support for " Andy Lutomirski
2017-11-22 12:10   ` Borislav Petkov
2017-11-22  4:43 ` [PATCH v2 04/18] x86/gdt: Put per-cpu GDT remaps in ascending order Andy Lutomirski
2017-11-22 11:05   ` Borislav Petkov
2017-11-22 15:26     ` Andy Lutomirski
2017-11-22  4:44 ` [PATCH v2 05/18] x86/fixmap: Generalize the GDT fixmap mechanism Andy Lutomirski
2017-11-22 15:33   ` Borislav Petkov
2017-11-22 17:16     ` Andy Lutomirski
2017-11-22 17:32       ` Borislav Petkov
2017-11-23 15:24         ` Andy Lutomirski
2017-11-23 19:24   ` Thomas Gleixner
2017-11-22  4:44 ` [PATCH v2 06/18] x86/kasan/64: Teach KASAN about the cpu_entry_area Andy Lutomirski
2017-11-22  6:19   ` Ingo Molnar
2017-11-22  9:05   ` Andrey Ryabinin
2017-11-22 15:22     ` Andy Lutomirski
2017-11-23 10:08       ` Andrey Ryabinin
2017-11-23 15:22         ` Andy Lutomirski
2017-11-22  4:44 ` [PATCH v2 07/18] x86/asm: Fix assumptions that the HW TSS is at the beginning of cpu_tss Andy Lutomirski
2017-11-22 19:06   ` Borislav Petkov
2017-11-22  4:44 ` [PATCH v2 08/18] x86/dumpstack: Handle stack overflow on all stacks Andy Lutomirski
2017-11-23 11:19   ` Borislav Petkov
2017-11-22  4:44 ` [PATCH v2 09/18] x86/asm: Move SYSENTER_stack to the beginning of struct tss_struct Andy Lutomirski
2017-11-23 12:00   ` Borislav Petkov
2017-11-23 13:16   ` Denys Vlasenko
2017-11-23 15:02     ` Andy Lutomirski
2017-11-23 19:30   ` Thomas Gleixner
2017-11-22  4:44 ` [PATCH v2 10/18] x86/asm: Remap the TSS into the cpu entry area Andy Lutomirski
2017-11-23 19:32   ` Thomas Gleixner
2017-11-23 19:55   ` Borislav Petkov
2017-11-23 20:15     ` Andy Lutomirski
2017-11-23 20:37       ` Borislav Petkov
2017-11-24  2:40         ` Andy Lutomirski
2017-11-24  4:17           ` Andy Lutomirski
2017-11-22  4:44 ` [PATCH v2 11/18] x86/asm/64: Separate cpu_current_top_of_stack from TSS.sp0 Andy Lutomirski
2017-11-23 19:34   ` Thomas Gleixner
2017-11-22  4:44 ` [PATCH v2 12/18] x86/espfix/64: Stop assuming that pt_regs is on the entry stack Andy Lutomirski
2017-11-23 19:36   ` Thomas Gleixner
2017-11-22  4:44 ` [PATCH v2 13/18] x86/asm/64: Use a percpu trampoline stack for IDT entries Andy Lutomirski
2017-11-23 23:44   ` Thomas Gleixner [this message]
2017-11-24  4:14     ` Andy Lutomirski
2017-11-22  4:44 ` [PATCH v2 14/18] x86/asm/64: Return to userspace from the trampoline stack Andy Lutomirski
2017-11-22  4:44 ` [PATCH v2 15/18] x86/entry/64: Create a percpu SYSCALL entry trampoline Andy Lutomirski
2017-11-22  4:44 ` [PATCH v2 16/18] x86/irq: Remove an old outdated comment about context tracking races Andy Lutomirski
2017-11-22  4:44 ` [PATCH v2 17/18] x86/irq/64: In the stack overflow warning, print the offending IP Andy Lutomirski
2017-11-22  4:44 ` [PATCH v2 18/18] x86/entry/64: Move the IST stacks into cpu_entry_area Andy Lutomirski
2017-11-22  6:22 ` [PATCH v2 00/18] Entry stack switching Ingo Molnar
2017-11-22  6:36   ` Ingo Molnar
2017-11-22 16:23   ` Andy Lutomirski
2017-11-23  6:21     ` Ingo Molnar
2017-11-23  6:44       ` Ingo Molnar
2017-11-23  6:58         ` Ingo Molnar
2017-11-23 15:29           ` Andy Lutomirski
2017-11-23 16:41             ` Thomas Gleixner
2017-11-22  7:39 ` WARNING: can't dereference registers at ffffc90004dfff60 for ip error_entry+0x7d/0xd0 (Re: [PATCH v2 00/18] Entry stack switching) Ingo Molnar
2017-11-22  7:43   ` Ingo Molnar
2017-11-22 13:55   ` Josh Poimboeuf
2017-11-22 15:19     ` Andy Lutomirski
2017-11-22 15:56       ` Ingo Molnar
2017-11-22 16:35         ` Andy Lutomirski

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.2.20.1711232239200.2364@nanos \
    --to=tglx@linutronix.de \
    --cc=bpetkov@suse.de \
    --cc=brgerst@gmail.com \
    --cc=dave.hansen@intel.com \
    --cc=jpoimboe@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@kernel.org \
    --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: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®