[PATCH 6/7] KVM: arm64: re-factor hyp.S debug register code

[Andrew Jones]

On Tue, Nov 25, 2014 at 04:10:04PM +0000, Alex Bennée wrote:
> This is a pre-cursor to sharing the code with the guest debug support.
> This replaces the big macro that fishes data out of a fixed location
> with a more general helper macro to restore a set of debug registers. It
> uses macro substitution so it can be re-used for debug control and value
> registers. It does however rely on the debug registers being 64 bit
> aligned (as they happen to be in the hyp ABI).
> 
> Signed-off-by: Alex Bennée <alex.bennee at linaro.org>
> 
> diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
> index c0bc218..b38ce3d 100644
> --- a/arch/arm64/kvm/hyp.S
> +++ b/arch/arm64/kvm/hyp.S
> @@ -490,65 +490,12 @@
>  	msr	mdscr_el1,	x25
>  .endm
>  
> -.macro restore_debug
> -	// x2: base address for cpu context
> -	// x3: tmp register
> -
> -	mrs	x26, id_aa64dfr0_el1
> -	ubfx	x24, x26, #12, #4	// Extract BRPs
> -	ubfx	x25, x26, #20, #4	// Extract WRPs
> -	mov	w26, #15
> -	sub	w24, w26, w24		// How many BPs to skip
> -	sub	w25, w26, w25		// How many WPs to skip
> -
> -	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1)
> -
> -	adr	x26, 1f
> -	add	x26, x26, x24, lsl #2
> -	br	x26
> -1:
> -	ldr	x20, [x3, #(15 * 8)]
> -	ldr	x19, [x3, #(14 * 8)]
> -	ldr	x18, [x3, #(13 * 8)]
> -	ldr	x17, [x3, #(12 * 8)]
> -	ldr	x16, [x3, #(11 * 8)]
> -	ldr	x15, [x3, #(10 * 8)]
> -	ldr	x14, [x3, #(9 * 8)]
> -	ldr	x13, [x3, #(8 * 8)]
> -	ldr	x12, [x3, #(7 * 8)]
> -	ldr	x11, [x3, #(6 * 8)]
> -	ldr	x10, [x3, #(5 * 8)]
> -	ldr	x9, [x3, #(4 * 8)]
> -	ldr	x8, [x3, #(3 * 8)]
> -	ldr	x7, [x3, #(2 * 8)]
> -	ldr	x6, [x3, #(1 * 8)]
> -	ldr	x5, [x3, #(0 * 8)]
> -
> +.macro setup_debug_registers type
> +        // x3: pointer to register set
> +        // x4: number of registers to copy
> +        // x5..x20/x26 trashed
                     ^ comma instead?
>  	adr	x26, 1f
> -	add	x26, x26, x24, lsl #2
> -	br	x26
> -1:
> -	msr	dbgbcr15_el1, x20
> -	msr	dbgbcr14_el1, x19
> -	msr	dbgbcr13_el1, x18
> -	msr	dbgbcr12_el1, x17
> -	msr	dbgbcr11_el1, x16
> -	msr	dbgbcr10_el1, x15
> -	msr	dbgbcr9_el1, x14
> -	msr	dbgbcr8_el1, x13
> -	msr	dbgbcr7_el1, x12
> -	msr	dbgbcr6_el1, x11
> -	msr	dbgbcr5_el1, x10
> -	msr	dbgbcr4_el1, x9
> -	msr	dbgbcr3_el1, x8
> -	msr	dbgbcr2_el1, x7
> -	msr	dbgbcr1_el1, x6
> -	msr	dbgbcr0_el1, x5
> -
> -	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1)
> -
> -	adr	x26, 1f
> -	add	x26, x26, x24, lsl #2
> +	add	x26, x26, x4, lsl #2
>  	br	x26
>  1:
>  	ldr	x20, [x3, #(15 * 8)]
> @@ -569,116 +516,25 @@
>  	ldr	x5, [x3, #(0 * 8)]
>  
>  	adr	x26, 1f
> -	add	x26, x26, x24, lsl #2
> -	br	x26
> -1:
> -	msr	dbgbvr15_el1, x20
> -	msr	dbgbvr14_el1, x19
> -	msr	dbgbvr13_el1, x18
> -	msr	dbgbvr12_el1, x17
> -	msr	dbgbvr11_el1, x16
> -	msr	dbgbvr10_el1, x15
> -	msr	dbgbvr9_el1, x14
> -	msr	dbgbvr8_el1, x13
> -	msr	dbgbvr7_el1, x12
> -	msr	dbgbvr6_el1, x11
> -	msr	dbgbvr5_el1, x10
> -	msr	dbgbvr4_el1, x9
> -	msr	dbgbvr3_el1, x8
> -	msr	dbgbvr2_el1, x7
> -	msr	dbgbvr1_el1, x6
> -	msr	dbgbvr0_el1, x5
> -
> -	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1)
> -
> -	adr	x26, 1f
> -	add	x26, x26, x25, lsl #2
> +	add	x26, x26, x4, lsl #2
>  	br	x26
>  1:
> -	ldr	x20, [x3, #(15 * 8)]
> -	ldr	x19, [x3, #(14 * 8)]
> -	ldr	x18, [x3, #(13 * 8)]
> -	ldr	x17, [x3, #(12 * 8)]
> -	ldr	x16, [x3, #(11 * 8)]
> -	ldr	x15, [x3, #(10 * 8)]
> -	ldr	x14, [x3, #(9 * 8)]
> -	ldr	x13, [x3, #(8 * 8)]
> -	ldr	x12, [x3, #(7 * 8)]
> -	ldr	x11, [x3, #(6 * 8)]
> -	ldr	x10, [x3, #(5 * 8)]
> -	ldr	x9, [x3, #(4 * 8)]
> -	ldr	x8, [x3, #(3 * 8)]
> -	ldr	x7, [x3, #(2 * 8)]
> -	ldr	x6, [x3, #(1 * 8)]
> -	ldr	x5, [x3, #(0 * 8)]
> -
> -	adr	x26, 1f
> -	add	x26, x26, x25, lsl #2
> -	br	x26
> -1:
> -	msr	dbgwcr15_el1, x20
> -	msr	dbgwcr14_el1, x19
> -	msr	dbgwcr13_el1, x18
> -	msr	dbgwcr12_el1, x17
> -	msr	dbgwcr11_el1, x16
> -	msr	dbgwcr10_el1, x15
> -	msr	dbgwcr9_el1, x14
> -	msr	dbgwcr8_el1, x13
> -	msr	dbgwcr7_el1, x12
> -	msr	dbgwcr6_el1, x11
> -	msr	dbgwcr5_el1, x10
> -	msr	dbgwcr4_el1, x9
> -	msr	dbgwcr3_el1, x8
> -	msr	dbgwcr2_el1, x7
> -	msr	dbgwcr1_el1, x6
> -	msr	dbgwcr0_el1, x5
> -
> -	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1)
> -
> -	adr	x26, 1f
> -	add	x26, x26, x25, lsl #2
> -	br	x26
> -1:
> -	ldr	x20, [x3, #(15 * 8)]
> -	ldr	x19, [x3, #(14 * 8)]
> -	ldr	x18, [x3, #(13 * 8)]
> -	ldr	x17, [x3, #(12 * 8)]
> -	ldr	x16, [x3, #(11 * 8)]
> -	ldr	x15, [x3, #(10 * 8)]
> -	ldr	x14, [x3, #(9 * 8)]
> -	ldr	x13, [x3, #(8 * 8)]
> -	ldr	x12, [x3, #(7 * 8)]
> -	ldr	x11, [x3, #(6 * 8)]
> -	ldr	x10, [x3, #(5 * 8)]
> -	ldr	x9, [x3, #(4 * 8)]
> -	ldr	x8, [x3, #(3 * 8)]
> -	ldr	x7, [x3, #(2 * 8)]
> -	ldr	x6, [x3, #(1 * 8)]
> -	ldr	x5, [x3, #(0 * 8)]
> -
> -	adr	x26, 1f
> -	add	x26, x26, x25, lsl #2
> -	br	x26
> -1:
> -	msr	dbgwvr15_el1, x20
> -	msr	dbgwvr14_el1, x19
> -	msr	dbgwvr13_el1, x18
> -	msr	dbgwvr12_el1, x17
> -	msr	dbgwvr11_el1, x16
> -	msr	dbgwvr10_el1, x15
> -	msr	dbgwvr9_el1, x14
> -	msr	dbgwvr8_el1, x13
> -	msr	dbgwvr7_el1, x12
> -	msr	dbgwvr6_el1, x11
> -	msr	dbgwvr5_el1, x10
> -	msr	dbgwvr4_el1, x9
> -	msr	dbgwvr3_el1, x8
> -	msr	dbgwvr2_el1, x7
> -	msr	dbgwvr1_el1, x6
> -	msr	dbgwvr0_el1, x5
> -
> -	ldr	x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
> -	msr	mdccint_el1, x21
> +	msr	\type\()15_el1, x20
> +	msr	\type\()14_el1, x19
> +	msr	\type\()13_el1, x18
> +	msr	\type\()12_el1, x17
> +	msr	\type\()11_el1, x16
> +	msr	\type\()10_el1, x15
> +	msr	\type\()9_el1, x14
> +	msr	\type\()8_el1, x13
> +	msr	\type\()7_el1, x12
> +	msr	\type\()6_el1, x11
> +	msr	\type\()5_el1, x10
> +	msr	\type\()4_el1, x9
> +	msr	\type\()3_el1, x8
> +	msr	\type\()2_el1, x7
> +	msr	\type\()1_el1, x6
> +	msr	\type\()0_el1, x5
>  .endm
>  
>  .macro skip_32bit_state tmp, target
> @@ -929,8 +785,34 @@ __save_debug:
>  	save_debug
>  	ret
>  
> +/* Restore saved guest debug state */
>  __restore_debug:
> -	restore_debug
> +	// x2: base address for cpu context
> +	// x3: ptr to guest registers passed to setup_debug_registers

I'm not sure we need to describe x3 here, as it's input for
setup_debug_registers, and thus described there. If it's preferred
though, then we should also describe x4.

> +	// x5..x20/x26: trashed

And x3 and x4, and x21,x24,x25

> +
> +	mrs	x26, id_aa64dfr0_el1
> +	ubfx	x24, x26, #12, #4	// Extract BRPs
> +	ubfx	x25, x26, #20, #4	// Extract WRPs
> +	mov	w26, #15
> +	sub	w24, w26, w24		// How many BPs to skip
> +	sub	w25, w26, w25		// How many WPs to skip
> +
> +	mov     x4, x24
> +	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1)
> +	setup_debug_registers dbgbcr
> +	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1)
> +	setup_debug_registers dbgbvr
> +
> +	mov     x4, x25
> +	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1)
> +	setup_debug_registers dbgwcr
> +	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1)
> +	setup_debug_registers dbgwvr
> +
> +	ldr	x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
> +	msr	mdccint_el1, x21
> +
>  	ret


How about doing the same refactoring on save_debug just for
consistency and code shrinkage?

>  
>  __save_fpsimd:
> -- 
> 2.1.3
> 
> _______________________________________________
> kvmarm mailing list
> kvmarm at lists.cs.columbia.edu
> https://lists.cs.columbia.edu/mailman/listinfo/kvmarm