[v4,2/2] arm64: enable context tracking

Message ID 7hd2f5icat.fsf@paris.lan
State New
Headers show

Commit Message

Kevin Hilman May 23, 2014, 12:11 a.m.
+Mark Rutland

Christopher Covington <cov@codeaurora.org> writes:

> Hi Larry,
>
> On 05/22/2014 03:27 PM, Larry Bassel wrote:
>> Make calls to ct_user_enter when the kernel is exited
>> and ct_user_exit when the kernel is entered (in el0_da,
>> el0_ia, el0_svc, el0_irq and all of the "error" paths).
>> 
>> These macros expand to function calls which will only work
>> properly if el0_sync and related code has been rearranged
>> (in a previous patch of this series).
>> 
>> The calls to ct_user_exit are made after hw debugging has been
>> enabled (enable_dbg_and_irq).
>> 
>> The call to ct_user_enter is made at the beginning of the
>> kernel_exit macro.
>> 
>> This patch is based on earlier work by Kevin Hilman.
>> Save/restore optimizations were also done by Kevin.
>
>> --- a/arch/arm64/kernel/entry.S
>> +++ b/arch/arm64/kernel/entry.S
>> @@ -30,6 +30,44 @@
>>  #include <asm/unistd32.h>
>>  
>>  /*
>> + * Context tracking subsystem.  Used to instrument transitions
>> + * between user and kernel mode.
>> + */
>> +	.macro ct_user_exit, restore = 0
>> +#ifdef CONFIG_CONTEXT_TRACKING
>> +	bl	context_tracking_user_exit
>> +	.if \restore == 1
>> +	/*
>> +	 * Save/restore needed during syscalls.  Restore syscall arguments from
>> +	 * the values already saved on stack during kernel_entry.
>> +	 */
>> +	ldp	x0, x1, [sp]
>> +	ldp	x2, x3, [sp, #S_X2]
>> +	ldp	x4, x5, [sp, #S_X4]
>> +	ldp	x6, x7, [sp, #S_X6]
>> +	.endif
>> +#endif
>> +	.endm
>> +
>> +	.macro ct_user_enter, save = 0
>> +#ifdef CONFIG_CONTEXT_TRACKING
>> +	.if \save == 1
>> +	/*
>> +	 * Save/restore only needed on syscall fastpath, which uses
>> +	 * x0-x2.
>> +	 */
>> +	push    x2, x3
>
> Why is x3 saved?

I'll respond here since I worked with Larry on the context save/restore
part.

[insert rather embarassing disclamer of ignorance of arm64 assembly]

Based on my reading of the code, I figured only x0-x2 needed to be
saved.  However, based on some experiments with intentionally clobbering
the registers[1] (as suggested by Mark Rutland) in order to make sure
we're saving/restoring the right things, I discovered x3 was needed too
(I missed updating the comment to mention x0-x3.)

Maybe Will/Catalin/Mark R. can shed some light here?

Kevin

[1]
From 8a8702b4d597d08def22221368beae5db2f4a8aa Mon Sep 17 00:00:00 2001
From: Kevin Hilman <khilman@linaro.org>
Date: Fri, 9 May 2014 13:37:43 -0700
Subject: [PATCH] KJH: test: clobber regs

---
 arch/arm64/kernel/entry.S | 38 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

Comments

Catalin Marinas May 23, 2014, 2:51 p.m. | #1
On Fri, May 23, 2014 at 01:11:38AM +0100, Kevin Hilman wrote:
> Christopher Covington <cov@codeaurora.org> writes:
> > On 05/22/2014 03:27 PM, Larry Bassel wrote:
> >> Make calls to ct_user_enter when the kernel is exited
> >> and ct_user_exit when the kernel is entered (in el0_da,
> >> el0_ia, el0_svc, el0_irq and all of the "error" paths).
> >> 
> >> These macros expand to function calls which will only work
> >> properly if el0_sync and related code has been rearranged
> >> (in a previous patch of this series).
> >> 
> >> The calls to ct_user_exit are made after hw debugging has been
> >> enabled (enable_dbg_and_irq).
> >> 
> >> The call to ct_user_enter is made at the beginning of the
> >> kernel_exit macro.
> >> 
> >> This patch is based on earlier work by Kevin Hilman.
> >> Save/restore optimizations were also done by Kevin.
> >
> >> --- a/arch/arm64/kernel/entry.S
> >> +++ b/arch/arm64/kernel/entry.S
> >> @@ -30,6 +30,44 @@
> >>  #include <asm/unistd32.h>
> >>  
> >>  /*
> >> + * Context tracking subsystem.  Used to instrument transitions
> >> + * between user and kernel mode.
> >> + */
> >> +	.macro ct_user_exit, restore = 0
> >> +#ifdef CONFIG_CONTEXT_TRACKING
> >> +	bl	context_tracking_user_exit
> >> +	.if \restore == 1
> >> +	/*
> >> +	 * Save/restore needed during syscalls.  Restore syscall arguments from
> >> +	 * the values already saved on stack during kernel_entry.
> >> +	 */
> >> +	ldp	x0, x1, [sp]
> >> +	ldp	x2, x3, [sp, #S_X2]
> >> +	ldp	x4, x5, [sp, #S_X4]
> >> +	ldp	x6, x7, [sp, #S_X6]
> >> +	.endif
> >> +#endif
> >> +	.endm
> >> +
> >> +	.macro ct_user_enter, save = 0
> >> +#ifdef CONFIG_CONTEXT_TRACKING
> >> +	.if \save == 1
> >> +	/*
> >> +	 * Save/restore only needed on syscall fastpath, which uses
> >> +	 * x0-x2.
> >> +	 */
> >> +	push    x2, x3
> >
> > Why is x3 saved?
> 
> I'll respond here since I worked with Larry on the context save/restore
> part.
> 
> [insert rather embarassing disclamer of ignorance of arm64 assembly]
> 
> Based on my reading of the code, I figured only x0-x2 needed to be
> saved.  However, based on some experiments with intentionally clobbering
> the registers[1] (as suggested by Mark Rutland) in order to make sure
> we're saving/restoring the right things, I discovered x3 was needed too
> (I missed updating the comment to mention x0-x3.)
> 
> Maybe Will/Catalin/Mark R. can shed some light here?

I haven't checked all the code paths but at least for pushing onto the
stack we must keep it 16-bytes aligned (architecture requirement).
Mark Rutland May 23, 2014, 3:55 p.m. | #2
On Fri, May 23, 2014 at 03:51:07PM +0100, Catalin Marinas wrote:
> On Fri, May 23, 2014 at 01:11:38AM +0100, Kevin Hilman wrote:
> > Christopher Covington <cov@codeaurora.org> writes:
> > > On 05/22/2014 03:27 PM, Larry Bassel wrote:
> > >> Make calls to ct_user_enter when the kernel is exited
> > >> and ct_user_exit when the kernel is entered (in el0_da,
> > >> el0_ia, el0_svc, el0_irq and all of the "error" paths).
> > >> 
> > >> These macros expand to function calls which will only work
> > >> properly if el0_sync and related code has been rearranged
> > >> (in a previous patch of this series).
> > >> 
> > >> The calls to ct_user_exit are made after hw debugging has been
> > >> enabled (enable_dbg_and_irq).
> > >> 
> > >> The call to ct_user_enter is made at the beginning of the
> > >> kernel_exit macro.
> > >> 
> > >> This patch is based on earlier work by Kevin Hilman.
> > >> Save/restore optimizations were also done by Kevin.
> > >
> > >> --- a/arch/arm64/kernel/entry.S
> > >> +++ b/arch/arm64/kernel/entry.S
> > >> @@ -30,6 +30,44 @@
> > >>  #include <asm/unistd32.h>
> > >>  
> > >>  /*
> > >> + * Context tracking subsystem.  Used to instrument transitions
> > >> + * between user and kernel mode.
> > >> + */
> > >> +	.macro ct_user_exit, restore = 0
> > >> +#ifdef CONFIG_CONTEXT_TRACKING
> > >> +	bl	context_tracking_user_exit
> > >> +	.if \restore == 1
> > >> +	/*
> > >> +	 * Save/restore needed during syscalls.  Restore syscall arguments from
> > >> +	 * the values already saved on stack during kernel_entry.
> > >> +	 */
> > >> +	ldp	x0, x1, [sp]
> > >> +	ldp	x2, x3, [sp, #S_X2]
> > >> +	ldp	x4, x5, [sp, #S_X4]
> > >> +	ldp	x6, x7, [sp, #S_X6]
> > >> +	.endif
> > >> +#endif
> > >> +	.endm
> > >> +
> > >> +	.macro ct_user_enter, save = 0
> > >> +#ifdef CONFIG_CONTEXT_TRACKING
> > >> +	.if \save == 1
> > >> +	/*
> > >> +	 * Save/restore only needed on syscall fastpath, which uses
> > >> +	 * x0-x2.
> > >> +	 */
> > >> +	push    x2, x3
> > >
> > > Why is x3 saved?
> > 
> > I'll respond here since I worked with Larry on the context save/restore
> > part.
> > 
> > [insert rather embarassing disclamer of ignorance of arm64 assembly]
> > 
> > Based on my reading of the code, I figured only x0-x2 needed to be
> > saved.  However, based on some experiments with intentionally clobbering
> > the registers[1] (as suggested by Mark Rutland) in order to make sure
> > we're saving/restoring the right things, I discovered x3 was needed too
> > (I missed updating the comment to mention x0-x3.)
> > 
> > Maybe Will/Catalin/Mark R. can shed some light here?
> 
> I haven't checked all the code paths but at least for pushing onto the
> stack we must keep it 16-bytes aligned (architecture requirement).

Sure -- if modifying the stack we need to push/pop pairs of registers to
keep it aligned. It might be better to use xzr as the dummy value in
that case to make it clear that the value doesn't really matter.

That said, ct_user_enter is only called in kernel_exit before we restore
the values off the stack, and the only register I can spot that we need
to preserve is x0 for the syscall return value. I can't see x1 or x2
being used any more specially than the rest of the remaining registers.
Am I missing something, or would it be sufficient to do the following?

push	x0, xzr
bl	context_tacking_user_enter
pop	x0, xzr

Cheers,
Mark.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
Will Deacon May 23, 2014, 4:12 p.m. | #3
On Fri, May 23, 2014 at 04:55:44PM +0100, Mark Rutland wrote:
> On Fri, May 23, 2014 at 03:51:07PM +0100, Catalin Marinas wrote:
> > On Fri, May 23, 2014 at 01:11:38AM +0100, Kevin Hilman wrote:
> > I haven't checked all the code paths but at least for pushing onto the
> > stack we must keep it 16-bytes aligned (architecture requirement).
> 
> Sure -- if modifying the stack we need to push/pop pairs of registers to
> keep it aligned. It might be better to use xzr as the dummy value in
> that case to make it clear that the value doesn't really matter.
> 
> That said, ct_user_enter is only called in kernel_exit before we restore
> the values off the stack, and the only register I can spot that we need
> to preserve is x0 for the syscall return value. I can't see x1 or x2
> being used any more specially than the rest of the remaining registers.
> Am I missing something, or would it be sufficient to do the following?
> 
> push	x0, xzr
> bl	context_tacking_user_enter
> pop	x0, xzr

... and if that works, then why are we using the stack instead of a
callee-saved register?

Will
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
Kevin Hilman May 24, 2014, 12:03 a.m. | #4
Mark Rutland <mark.rutland@arm.com> writes:

> On Fri, May 23, 2014 at 03:51:07PM +0100, Catalin Marinas wrote:
>> On Fri, May 23, 2014 at 01:11:38AM +0100, Kevin Hilman wrote:
>> > Christopher Covington <cov@codeaurora.org> writes:
>> > > On 05/22/2014 03:27 PM, Larry Bassel wrote:
>> > >> Make calls to ct_user_enter when the kernel is exited
>> > >> and ct_user_exit when the kernel is entered (in el0_da,
>> > >> el0_ia, el0_svc, el0_irq and all of the "error" paths).
>> > >> 
>> > >> These macros expand to function calls which will only work
>> > >> properly if el0_sync and related code has been rearranged
>> > >> (in a previous patch of this series).
>> > >> 
>> > >> The calls to ct_user_exit are made after hw debugging has been
>> > >> enabled (enable_dbg_and_irq).
>> > >> 
>> > >> The call to ct_user_enter is made at the beginning of the
>> > >> kernel_exit macro.
>> > >> 
>> > >> This patch is based on earlier work by Kevin Hilman.
>> > >> Save/restore optimizations were also done by Kevin.
>> > >
>> > >> --- a/arch/arm64/kernel/entry.S
>> > >> +++ b/arch/arm64/kernel/entry.S
>> > >> @@ -30,6 +30,44 @@
>> > >>  #include <asm/unistd32.h>
>> > >>  
>> > >>  /*
>> > >> + * Context tracking subsystem.  Used to instrument transitions
>> > >> + * between user and kernel mode.
>> > >> + */
>> > >> +	.macro ct_user_exit, restore = 0
>> > >> +#ifdef CONFIG_CONTEXT_TRACKING
>> > >> +	bl	context_tracking_user_exit
>> > >> +	.if \restore == 1
>> > >> +	/*
>> > >> +	 * Save/restore needed during syscalls.  Restore syscall arguments from
>> > >> +	 * the values already saved on stack during kernel_entry.
>> > >> +	 */
>> > >> +	ldp	x0, x1, [sp]
>> > >> +	ldp	x2, x3, [sp, #S_X2]
>> > >> +	ldp	x4, x5, [sp, #S_X4]
>> > >> +	ldp	x6, x7, [sp, #S_X6]
>> > >> +	.endif
>> > >> +#endif
>> > >> +	.endm
>> > >> +
>> > >> +	.macro ct_user_enter, save = 0
>> > >> +#ifdef CONFIG_CONTEXT_TRACKING
>> > >> +	.if \save == 1
>> > >> +	/*
>> > >> +	 * Save/restore only needed on syscall fastpath, which uses
>> > >> +	 * x0-x2.
>> > >> +	 */
>> > >> +	push    x2, x3
>> > >
>> > > Why is x3 saved?
>> > 
>> > I'll respond here since I worked with Larry on the context save/restore
>> > part.
>> > 
>> > [insert rather embarassing disclamer of ignorance of arm64 assembly]
>> > 
>> > Based on my reading of the code, I figured only x0-x2 needed to be
>> > saved.  However, based on some experiments with intentionally clobbering
>> > the registers[1] (as suggested by Mark Rutland) in order to make sure
>> > we're saving/restoring the right things, I discovered x3 was needed too
>> > (I missed updating the comment to mention x0-x3.)
>> > 
>> > Maybe Will/Catalin/Mark R. can shed some light here?
>> 
>> I haven't checked all the code paths but at least for pushing onto the
>> stack we must keep it 16-bytes aligned (architecture requirement).
>
> Sure -- if modifying the stack we need to push/pop pairs of registers to
> keep it aligned. It might be better to use xzr as the dummy value in
> that case to make it clear that the value doesn't really matter.
>
> That said, ct_user_enter is only called in kernel_exit before we restore
> the values off the stack, and the only register I can spot that we need
> to preserve is x0 for the syscall return value. I can't see x1 or x2
> being used any more specially than the rest of the remaining registers.
> Am I missing something,

I don't think you're missing something.  I had thought my experiment in
clobbering registers uncovered that x1-x3 were also in use somewhere,
but in trying to reproduce that now, it's clear only x0 is important.

> or would it be sufficient to do the following?
> push	x0, xzr
> bl	context_tacking_user_enter
> pop	x0, xzr

Yes, this seems to work.

Following Will's suggestion of using a callee-saved register to save x0,
the updated version now looks like this:

	.macro ct_user_enter, save = 0
#ifdef CONFIG_CONTEXT_TRACKING
	.if \save == 1
	/*
	 * We only have to save/restore x0 on the fast syscall path where
	 * x0 contains the syscall return.
	 */
	mov	x19, x0
	.endif
	bl	context_tracking_user_enter
	.if \save == 1
	mov	x0, x19
	.endif
#endif
	.endm


We'll update this as well as address the comments on PATCH 1/2 and send
a v5.

Thanks guys for the review and guidance as I'm wandering a bit in the
dark here in arm64 assembler land.

Cheers,

Kevin

Patch

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 520da4c02ece..232f0200e88d 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -36,6 +36,25 @@ 
 	.macro ct_user_exit, restore = 0
 #ifdef CONFIG_CONTEXT_TRACKING
 	bl	context_tracking_user_exit
+ 	movz	x0, #0xff, lsl #48
+	movz	x1, #0xff, lsl #48
+	movz	x2, #0xff, lsl #48
+	movz	x3, #0xff, lsl #48
+	movz	x4, #0xff, lsl #48
+	movz	x5, #0xff, lsl #48
+	movz	x6, #0xff, lsl #48
+	movz	x7, #0xff, lsl #48
+	movz	x8, #0xff, lsl #48
+	movz	x9, #0xff, lsl #48
+	movz	x10, #0xff, lsl #48
+	movz	x11, #0xff, lsl #48
+	movz	x12, #0xff, lsl #48
+	movz	x13, #0xff, lsl #48
+	movz	x14, #0xff, lsl #48
+	movz	x15, #0xff, lsl #48
+	movz	x16, #0xff, lsl #48
+	movz	x17, #0xff, lsl #48
+	movz	x18, #0xff, lsl #48
 	.if \restore == 1
 	/*
 	 * Save/restore needed during syscalls.  Restore syscall arguments from
@@ -60,6 +79,25 @@ 
 	push    x0, x1
 	.endif
 	bl	context_tracking_user_enter
+ 	movz	x0, #0xff, lsl #48
+	movz	x1, #0xff, lsl #48
+	movz	x2, #0xff, lsl #48
+	movz	x3, #0xff, lsl #48
+	movz	x4, #0xff, lsl #48
+	movz	x5, #0xff, lsl #48
+	movz	x6, #0xff, lsl #48
+	movz	x7, #0xff, lsl #48
+	movz	x8, #0xff, lsl #48
+	movz	x9, #0xff, lsl #48
+	movz	x10, #0xff, lsl #48
+	movz	x11, #0xff, lsl #48
+	movz	x12, #0xff, lsl #48
+	movz	x13, #0xff, lsl #48
+	movz	x14, #0xff, lsl #48
+	movz	x15, #0xff, lsl #48
+	movz	x16, #0xff, lsl #48
+	movz	x17, #0xff, lsl #48
+	movz	x18, #0xff, lsl #48
 	.if \save == 1
 	pop     x0, x1
 	pop     x2, x3