linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Alexandre Chartre <alexandre.chartre@oracle.com>
To: Thomas Gleixner <tglx@linutronix.de>,
	LKML <linux-kernel@vger.kernel.org>
Cc: x86@kernel.org, "Paul E. McKenney" <paulmck@kernel.org>,
	Andy Lutomirski <luto@kernel.org>,
	Frederic Weisbecker <frederic@kernel.org>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Sean Christopherson <sean.j.christopherson@intel.com>,
	Masami Hiramatsu <mhiramat@kernel.org>,
	Petr Mladek <pmladek@suse.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Joel Fernandes <joel@joelfernandes.org>,
	Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	Juergen Gross <jgross@suse.com>, Brian Gerst <brgerst@gmail.com>,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Josh Poimboeuf <jpoimboe@redhat.com>,
	Will Deacon <will@kernel.org>
Subject: Re: [patch V4 part 5 02/31] x86/entry: Provide helpers for execute on irqstack
Date: Mon, 11 May 2020 11:07:43 +0200	[thread overview]
Message-ID: <7477e59e-50d9-3446-dce7-3aa07e74cf5f@oracle.com> (raw)
In-Reply-To: <20200505135828.316937774@linutronix.de>


On 5/5/20 3:53 PM, Thomas Gleixner wrote:
> Device interrupt handlers and system vector handlers are executed on the
> interrupt stack. The stack switch happens in the low level assembly entry
> code. This conflicts with the efforts to consolidate the exit code in C to
> ensure correctness vs. RCU and tracing.
> 
> As there is no way to move #DB away from IST due to the MOV SS issue, the
> requirements vs. #DB and NMI for switching to the interrupt stack do not
> exist anymore. The only requirement is that interrupts are disabled.
> 
> That allows to move the stack switching to C code which simplifies the
> entry/exit handling further because it allows to switch stacks after
> handling the entry and on exit before handling RCU, return to usermode and
> kernel preemption in the same way as for regular exceptions.
> 
> That also allows to move the xen hypercall extra magic code and the softirq
> stack switching into C.
> 
> The mechanism is straight forward:
> 
>    1) Store the current stack pointer on top of the interrupt stack. That's
>       required for the unwinder.
> 
>    2) Switch the stack pointer
> 
>    3) Call the function
> 
>    4) Restore the stackpointer
> 
> The full code sequence to make the unwinder happy is:
> 
>      	pushq	%rbp
> 	movq	%rsp, %rbp
> 	movq    $(top_of_hardirq_stack - 8), %reg
> 	movq	%rsp, (%reg)
>    	movq	%reg , %rsp
> 	call    function
> 	popq	%rsp
> 	leaveq
> 	
> While the following sequence would spare the 'popq %rsp':
> 
>      	pushq	%rbp
> 	movq    $(top_of_hardirq_stack - 8), %rbp
> 	movq	%rsp, (%rrbp)

Should be (%rbp) instead of  (%rrbp).


>    	xchgq	%rbp, %rsp
> 	call    function
>   	movq	%rbp, %rsp
> 	leaveq
> 
> but that requires further changes to objtool so that the unwinder works
> correctly. Can be done on top and is not critical for now.
> 
> Provide helper functions to check whether the interrupt stack is already
> active and whether stack switching is required.
> 
> 64 bit only for now. 32 bit has a variant of that already. Once this is
> cleaned up the two implementations might be consolidated as a cleanup on
> top.
> 
> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
> ---
>   arch/x86/include/asm/irq_stack.h |   61 +++++++++++++++++++++++++++++++++++++++
>   1 file changed, 61 insertions(+)
> 
> --- /dev/null
> +++ b/arch/x86/include/asm/irq_stack.h
...
> +/*
> + * Macro to emit code for running @func on the irq stack.
> + */
> +#define RUN_ON_IRQSTACK(func)	{					\
> +	unsigned long tos;						\
> +									\
> +	lockdep_assert_irqs_disabled();					\
> +									\
> +	tos = ((unsigned long)__this_cpu_read(hardirq_stack_ptr)) - 8;	\
> +									\
> +	__this_cpu_add(irq_count, 1);					\
> +	asm volatile(							\
> +		"pushq  %%rbp					\n"	\
> +		"movq   %%rsp, %%rbp				\n"	\
> +		"movq	%%rsp, (%[ts])				\n"	\
> +		"movq	%[ts], %%rsp				\n"	\
> +		"1:						\n"	\
> +		"	.pushsection .discard.instr_begin	\n"	\
> +		"	.long 1b - .				\n"	\
> +		"	.popsection				\n"	\
> +		"call	" __ASM_FORM(func) "			\n"	\
> +		"2:						\n"	\
> +		"	.pushsection .discard.instr_end		\n"	\
> +		"	.long 2b - .				\n"	\
> +		"	.popsection				\n"	\
> +		"popq	%%rsp					\n"	\
> +		"leaveq						\n"	\
> +		:							\
> +		: [ts] "r" (tos)					\
> +		: "memory"						\
> +		);							\
> +	__this_cpu_sub(irq_count, 1);					\
> +}

The pushsection/popsection discard.instr_begin/end sequences are used several
times in asm() statement at different places, so I wonder if it might be worth
having a macro.

In part 1, patch 20/36 adds instr_begin()/end(): they provide the sequence
but already encapsulated into an asm() statement, then we could do something
like this:

/* Begin/end of an instrumentation safe region */
#define instr_begin_insn(label)				\
	__stringify(label) ":\n\t"			\
	".pushsection .discard.instr_begin\n\t"		\
	".long " __stringify(label) "b - .\n\t"		\
	".popsection\n\t"

#define instr_end_insn(label)				\
	__stringify(label) ":\n\t"			\
	".pushsection .discard.instr_end\n\t"		\
	".long " __stringify(label) "b - .\n\t"		\
	".popsection\n\t"

#define instr_begin() ({asm volatile(instr_begin_insn(__COUNTER__));})
#define instr_end() ({asm volatile(instr_end_insn(__COUNTER__));})> +#else /* CONFIG_X86_64 */

And the RUN_ON_IRQSTACK macro would become:

#define RUN_ON_IRQSTACK(func)	{					\
	unsigned long tos;						\
									\
	lockdep_assert_irqs_disabled();					\
									\
	tos = ((unsigned long)__this_cpu_read(hardirq_stack_ptr)) - 8;	\
									\
	__this_cpu_add(irq_count, 1);					\
	asm volatile(							\
		"pushq  %%rbp					\n"	\
		"movq   %%rsp, %%rbp				\n"	\
		"movq	%%rsp, (%[ts])				\n"	\
		"movq	%[ts], %%rsp				\n"	\
		instr_begin_insn(1)					\
		"call	" __ASM_FORM(func) "			\n"	\
		instr_end_insn(2)					\
		"popq	%%rsp					\n"	\
		"leaveq						\n"	\
		:							\
		: [ts] "r" (tos)					\
		: "memory"						\
		);							\
	__this_cpu_sub(irq_count, 1);					\
}

alex.

  parent reply	other threads:[~2020-05-11  9:09 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-05 13:53 [patch V4 part 5 00/31] x86/entry: Entry/exception code rework, Thomas Gleixner
2020-05-05 13:53 ` [patch V4 part 5 01/31] genirq: Provide irq_enter/exit_rcu() Thomas Gleixner
2020-05-15  5:53   ` Andy Lutomirski
2020-05-05 13:53 ` [patch V4 part 5 02/31] x86/entry: Provide helpers for execute on irqstack Thomas Gleixner
2020-05-06  8:20   ` Thomas Gleixner
2020-05-10  4:33   ` Lai Jiangshan
2020-05-11  9:07   ` Alexandre Chartre [this message]
2020-05-11 11:54     ` Thomas Gleixner
2020-05-05 13:53 ` [patch V4 part 5 03/31] x86/entry/64: Move softirq stack switch to C Thomas Gleixner
2020-05-05 13:53 ` [patch V4 part 5 04/31] x86/entry: Split idtentry_enter/exit() Thomas Gleixner
2020-05-11 12:42   ` Alexandre Chartre
2020-05-05 13:53 ` [patch V4 part 5 05/31] x86/entry: Switch XEN/PV hypercall entry to IDTENTRY Thomas Gleixner
2020-05-07  2:11   ` Boris Ostrovsky
2020-05-07  8:30     ` Thomas Gleixner
2020-05-05 13:53 ` [patch V4 part 5 06/31] x86/entry/64: Simplify idtentry_body Thomas Gleixner
2020-05-05 13:53 ` [patch V4 part 5 07/31] x86/entry: Provide idtentry_entry/exit_cond_rcu() Thomas Gleixner
2020-05-11 13:53   ` Alexandre Chartre
2020-05-11 14:13     ` Peter Zijlstra
2020-05-12 16:30     ` Thomas Gleixner
2020-05-05 13:53 ` [patch V4 part 5 08/31] x86/entry: Switch page fault exception to IDTENTRY_RAW Thomas Gleixner
2020-05-05 13:53 ` [patch V4 part 5 09/31] x86/entry: Remove the transition leftovers Thomas Gleixner
2020-05-11 14:11   ` Alexandre Chartre
2020-05-05 13:53 ` [patch V4 part 5 10/31] x86/entry: Change exit path of xen_failsafe_callback Thomas Gleixner
2020-05-05 13:53 ` [patch V4 part 5 11/31] x86/entry/64: Remove error_exit Thomas Gleixner
2020-05-05 13:53 ` [patch V4 part 5 12/31] x86/entry/32: Remove common_exception Thomas Gleixner
2020-05-05 13:53 ` [patch V4 part 5 13/31] x86/irq: Convey vector as argument and not in ptregs Thomas Gleixner
2020-05-10  2:44   ` Lai Jiangshan
2020-05-11 14:35     ` Thomas Gleixner
2020-05-11 15:11       ` Lai Jiangshan
2020-05-05 13:53 ` [patch V4 part 5 14/31] x86/irq/64: Provide handle_irq() Thomas Gleixner
2020-05-05 13:53 ` [patch V4 part 5 15/31] x86/entry: Add IRQENTRY_IRQ macro Thomas Gleixner
2020-05-05 13:53 ` [patch V4 part 5 16/31] x86/entry: Use idtentry for interrupts Thomas Gleixner
2020-05-05 13:53 ` [patch V4 part 5 17/31] x86/entry: Provide IDTENTRY_SYSVEC Thomas Gleixner
2020-05-05 13:53 ` [patch V4 part 5 18/31] x86/entry: Convert APIC interrupts to IDTENTRY_SYSVEC Thomas Gleixner
2020-05-05 13:54 ` [patch V4 part 5 19/31] x86/entry: Convert SMP system vectors " Thomas Gleixner
2020-05-05 13:54 ` [patch V4 part 5 20/31] x86/entry: Convert various system vectors Thomas Gleixner
2020-05-05 13:54 ` [patch V4 part 5 21/31] x86/entry: Convert KVM vectors to IDTENTRY_SYSVEC Thomas Gleixner
2020-05-05 13:54 ` [patch V4 part 5 22/31] x86/entry: Convert various hypervisor " Thomas Gleixner
2020-05-06 16:56   ` Wei Liu
2020-05-06 17:11     ` Thomas Gleixner
2020-05-05 13:54 ` [patch V4 part 5 23/31] x86/entry: Convert XEN hypercall vector " Thomas Gleixner
2020-05-05 13:54 ` [patch V4 part 5 24/31] x86/entry: Convert reschedule interrupt to IDTENTRY_RAW Thomas Gleixner
2020-05-05 13:54 ` [patch V4 part 5 25/31] x86/entry: Remove the apic/BUILD interrupt leftovers Thomas Gleixner
2020-05-05 13:54 ` [patch V4 part 5 26/31] x86/entry/64: Remove IRQ stack switching ASM Thomas Gleixner
2020-05-05 13:54 ` [patch V4 part 5 27/31] x86/entry: Make enter_from_user_mode() static Thomas Gleixner
2020-05-05 13:54 ` [patch V4 part 5 28/31] x86/entry/32: Remove redundant irq disable code Thomas Gleixner
2020-05-05 13:54 ` [patch V4 part 5 29/31] x86/entry/64: Remove TRACE_IRQS_*_DEBUG Thomas Gleixner
2020-05-05 13:54 ` [patch V4 part 5 30/31] x86/entry: Move paranoid irq tracing out of ASM code Thomas Gleixner
2020-05-05 13:54 ` [patch V4 part 5 31/31] x86/entry: Remove the TRACE_IRQS cruft Thomas Gleixner

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=7477e59e-50d9-3446-dce7-3aa07e74cf5f@oracle.com \
    --to=alexandre.chartre@oracle.com \
    --cc=boris.ostrovsky@oracle.com \
    --cc=brgerst@gmail.com \
    --cc=frederic@kernel.org \
    --cc=jgross@suse.com \
    --cc=joel@joelfernandes.org \
    --cc=jpoimboe@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mhiramat@kernel.org \
    --cc=paulmck@kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=pmladek@suse.com \
    --cc=rostedt@goodmis.org \
    --cc=sean.j.christopherson@intel.com \
    --cc=tglx@linutronix.de \
    --cc=will@kernel.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;
as well as URLs for NNTP newsgroup(s).