Re: [Xen-devel] [PATCH] xen: arm: arm64: Adding VFP save/restore support.

[Pranavkumar Sawargaonkar <pranavkumar@xxxxxxxxxx>]

Hi Ian,

On 6 February 2014 15:45, Ian Campbell <Ian.Campbell@xxxxxxxxxx> wrote:
> On Thu, 2014-02-06 at 12:58 +0530, Pranavkumar Sawargaonkar wrote:
>> This patch adds VFP save/restore support form arm64 across context switch.
>>
>> Signed-off-by: Pranavkumar Sawargaonkar <pranavkumar@xxxxxxxxxx>
>> Signed-off-by: Anup Patel <anup.patel@xxxxxxxxxx>
>
> This should go in for 4.4 -- not context switching floating point
> registers is obviously a big problem. (bit embarrassed that I forgot
> about this...)
>
>> ---
>>  xen/arch/arm/arm64/vfp.c        |   49 
>> +++++++++++++++++++++++++++++++++++++++
>>  xen/include/asm-arm/arm64/vfp.h |    4 ++++
>>  2 files changed, 53 insertions(+)
>>
>> diff --git a/xen/arch/arm/arm64/vfp.c b/xen/arch/arm/arm64/vfp.c
>> index 74e6a50..8c1479a 100644
>> --- a/xen/arch/arm/arm64/vfp.c
>> +++ b/xen/arch/arm/arm64/vfp.c
>> @@ -1,13 +1,62 @@
>>  #include <xen/sched.h>
>>  #include <asm/processor.h>
>> +#include <asm/cpufeature.h>
>>  #include <asm/vfp.h>
>>
>>  void vfp_save_state(struct vcpu *v)
>>  {
>>      /* TODO: implement it */
>
> You can probably remove this comment, and the one in restore, unless
> there is something still left to do?
Oops, sorry let me remove and repost it.

>
> Actually, I'll do it on commit, so:
> Acked-by: Ian Campbell <ian.campbell@xxxxxxxxxx>
>
>> +    if ( !cpu_has_fp )
>> +        return;
>> +
>> +    asm volatile("stp q0, q1, [%0, #16 * 0]\n\t"
>> +                 "stp q2, q3, [%0, #16 * 2]\n\t"
>> +                 "stp q4, q5, [%0, #16 * 4]\n\t"
>> +                 "stp q6, q7, [%0, #16 * 6]\n\t"
>> +                 "stp q8, q9, [%0, #16 * 8]\n\t"
>> +                 "stp q10, q11, [%0, #16 * 10]\n\t"
>> +                 "stp q12, q13, [%0, #16 * 12]\n\t"
>> +                 "stp q14, q15, [%0, #16 * 14]\n\t"
>> +                 "stp q16, q17, [%0, #16 * 16]\n\t"
>> +                 "stp q18, q19, [%0, #16 * 18]\n\t"
>> +                 "stp q20, q21, [%0, #16 * 20]\n\t"
>> +                 "stp q22, q23, [%0, #16 * 22]\n\t"
>> +                 "stp q24, q25, [%0, #16 * 24]\n\t"
>> +                 "stp q26, q27, [%0, #16 * 26]\n\t"
>> +                 "stp q28, q29, [%0, #16 * 28]\n\t"
>> +                 "stp q30, q31, [%0, #16 * 30]\n\t"
>> +                 :: "r" ((char *)(&v->arch.vfp.fpregs)): "memory");
>> +
>> +    v->arch.vfp.fpsr = READ_SYSREG32(FPSR);
>> +    v->arch.vfp.fpcr = READ_SYSREG32(FPCR);
>> +    v->arch.vfp.fpexc32_el2 = READ_SYSREG32(FPEXC32_EL2);
>>  }
>>
>>  void vfp_restore_state(struct vcpu *v)
>>  {
>>      /* TODO: implement it */
>> +    if ( !cpu_has_fp )
>> +        return;
>> +
>> +    asm volatile("ldp q0, q1, [%0, #16 * 0]\n\t"
>> +                 "ldp q2, q3, [%0, #16 * 2]\n\t"
>> +                 "ldp q4, q5, [%0, #16 * 4]\n\t"
>> +                 "ldp q6, q7, [%0, #16 * 6]\n\t"
>> +                 "ldp q8, q9, [%0, #16 * 8]\n\t"
>> +                 "ldp q10, q11, [%0, #16 * 10]\n\t"
>> +                 "ldp q12, q13, [%0, #16 * 12]\n\t"
>> +                 "ldp q14, q15, [%0, #16 * 14]\n\t"
>> +                 "ldp q16, q17, [%0, #16 * 16]\n\t"
>> +                 "ldp q18, q19, [%0, #16 * 18]\n\t"
>> +                 "ldp q20, q21, [%0, #16 * 20]\n\t"
>> +                 "ldp q22, q23, [%0, #16 * 22]\n\t"
>> +                 "ldp q24, q25, [%0, #16 * 24]\n\t"
>> +                 "ldp q26, q27, [%0, #16 * 26]\n\t"
>> +                 "ldp q28, q29, [%0, #16 * 28]\n\t"
>> +                 "ldp q30, q31, [%0, #16 * 30]\n\t"
>> +                 :: "r" ((char *)(&v->arch.vfp.fpregs)): "memory");
>> +
>> +    WRITE_SYSREG32(v->arch.vfp.fpsr, FPSR);
>> +    WRITE_SYSREG32(v->arch.vfp.fpcr, FPCR);
>> +    WRITE_SYSREG32(v->arch.vfp.fpexc32_el2, FPEXC32_EL2);
>>  }
>> diff --git a/xen/include/asm-arm/arm64/vfp.h 
>> b/xen/include/asm-arm/arm64/vfp.h
>> index 3733d2c..373f156 100644
>> --- a/xen/include/asm-arm/arm64/vfp.h
>> +++ b/xen/include/asm-arm/arm64/vfp.h
>> @@ -3,6 +3,10 @@
>>
>>  struct vfp_state
>>  {
>> +    uint64_t fpregs[64];
>> +    uint32_t fpcr;
>> +    uint32_t fpexc32_el2;
>> +    uint32_t fpsr;
>>  };
>>
>>  #endif /* _ARM_ARM64_VFP_H */
>
>
Thanks,
Pranav

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel