On 12/21/25 05:07, Chang S. Bae wrote:
> Add helpers to directly read and write EGPRs (R16–R31).
>
> Unlike legacy GPRs, EGPRs are not cached in vcpu->arch.regs[]. Their
> contents remain live in hardware. If preempted, the EGPR state is
> preserved in the guest XSAVE buffer.
>
> The Advanced Performance Extensions (APX) feature introduces EGPRs as an
> XSAVE-managed state component. The new helpers access the registers
> directly between kvm_fpu_get() and kvm_fpu_put().
>
> Callers should ensure that EGPRs are enabled before using these helpers.
>
> Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
> ---
> No change since last version
> ---
> arch/x86/kvm/fpu.h | 80 ++++++++++++++++++++++++++++++++++++++++++++--
> 1 file changed, 78 insertions(+), 2 deletions(-)
>
> diff --git a/arch/x86/kvm/fpu.h b/arch/x86/kvm/fpu.h
> index f2613924532d..f132cad4b49e 100644
> --- a/arch/x86/kvm/fpu.h
> +++ b/arch/x86/kvm/fpu.h
> @@ -148,6 +148,61 @@ static inline void _kvm_write_mmx_reg(int reg, const u64 *data)
> }
> }
>
> +#ifdef CONFIG_X86_64
> +/*
> + * Accessors for extended general-purpose registers. binutils >= 2.43 can
> + * recognize those register symbols.
> + */
> +
> +static inline void _kvm_read_egpr(int reg, unsigned long *data)
> +{
> + /* mov %r16..%r31, %rax */
> + switch (reg) {
> + case __VCPU_XREG_R16: asm(".byte 0xd5, 0x48, 0x89, 0xc0" : "=a"(*data)); break;
> + case __VCPU_XREG_R17: asm(".byte 0xd5, 0x48, 0x89, 0xc8" : "=a"(*data)); break;
> + case __VCPU_XREG_R18: asm(".byte 0xd5, 0x48, 0x89, 0xd0" : "=a"(*data)); break;
> + case __VCPU_XREG_R19: asm(".byte 0xd5, 0x48, 0x89, 0xd8" : "=a"(*data)); break;
> + case __VCPU_XREG_R20: asm(".byte 0xd5, 0x48, 0x89, 0xe0" : "=a"(*data)); break;
> + case __VCPU_XREG_R21: asm(".byte 0xd5, 0x48, 0x89, 0xe8" : "=a"(*data)); break;
> + case __VCPU_XREG_R22: asm(".byte 0xd5, 0x48, 0x89, 0xf0" : "=a"(*data)); break;
> + case __VCPU_XREG_R23: asm(".byte 0xd5, 0x48, 0x89, 0xf8" : "=a"(*data)); break;
> + case __VCPU_XREG_R24: asm(".byte 0xd5, 0x4c, 0x89, 0xc0" : "=a"(*data)); break;
> + case __VCPU_XREG_R25: asm(".byte 0xd5, 0x4c, 0x89, 0xc8" : "=a"(*data)); break;
> + case __VCPU_XREG_R26: asm(".byte 0xd5, 0x4c, 0x89, 0xd0" : "=a"(*data)); break;
> + case __VCPU_XREG_R27: asm(".byte 0xd5, 0x4c, 0x89, 0xd8" : "=a"(*data)); break;
> + case __VCPU_XREG_R28: asm(".byte 0xd5, 0x4c, 0x89, 0xe0" : "=a"(*data)); break;
> + case __VCPU_XREG_R29: asm(".byte 0xd5, 0x4c, 0x89, 0xe8" : "=a"(*data)); break;
> + case __VCPU_XREG_R30: asm(".byte 0xd5, 0x4c, 0x89, 0xf0" : "=a"(*data)); break;
> + case __VCPU_XREG_R31: asm(".byte 0xd5, 0x4c, 0x89, 0xf8" : "=a"(*data)); break;
> + default: BUG();
> + }
> +}
> +
> +static inline void _kvm_write_egpr(int reg, unsigned long *data)
> +{
> + /* mov %rax, %r16...%r31*/
> + switch (reg) {
> + case __VCPU_XREG_R16: asm(".byte 0xd5, 0x18, 0x89, 0xc0" : : "a"(*data)); break;
> + case __VCPU_XREG_R17: asm(".byte 0xd5, 0x18, 0x89, 0xc1" : : "a"(*data)); break;
> + case __VCPU_XREG_R18: asm(".byte 0xd5, 0x18, 0x89, 0xc2" : : "a"(*data)); break;
> + case __VCPU_XREG_R19: asm(".byte 0xd5, 0x18, 0x89, 0xc3" : : "a"(*data)); break;
> + case __VCPU_XREG_R20: asm(".byte 0xd5, 0x18, 0x89, 0xc4" : : "a"(*data)); break;
> + case __VCPU_XREG_R21: asm(".byte 0xd5, 0x18, 0x89, 0xc5" : : "a"(*data)); break;
> + case __VCPU_XREG_R22: asm(".byte 0xd5, 0x18, 0x89, 0xc6" : : "a"(*data)); break;
> + case __VCPU_XREG_R23: asm(".byte 0xd5, 0x18, 0x89, 0xc7" : : "a"(*data)); break;
> + case __VCPU_XREG_R24: asm(".byte 0xd5, 0x19, 0x89, 0xc0" : : "a"(*data)); break;
> + case __VCPU_XREG_R25: asm(".byte 0xd5, 0x19, 0x89, 0xc1" : : "a"(*data)); break;
> + case __VCPU_XREG_R26: asm(".byte 0xd5, 0x19, 0x89, 0xc2" : : "a"(*data)); break;
> + case __VCPU_XREG_R27: asm(".byte 0xd5, 0x19, 0x89, 0xc3" : : "a"(*data)); break;
> + case __VCPU_XREG_R28: asm(".byte 0xd5, 0x19, 0x89, 0xc4" : : "a"(*data)); break;
> + case __VCPU_XREG_R29: asm(".byte 0xd5, 0x19, 0x89, 0xc5" : : "a"(*data)); break;
> + case __VCPU_XREG_R30: asm(".byte 0xd5, 0x19, 0x89, 0xc6" : : "a"(*data)); break;
> + case __VCPU_XREG_R31: asm(".byte 0xd5, 0x19, 0x89, 0xc7" : : "a"(*data)); break;
> + default: BUG();
> + }
> +}
> +#endif
These are also way too big for inlining; move them in x86.c. Already in
patch 2,
+#ifdef CONFIG_X86_64
+static inline unsigned long kvm_read_egpr(int reg) { return 0; }
+static inline void kvm_write_egpr(int reg, unsigned long data) { }
+#endif
can be in x86.c.
Paolo
> static inline void kvm_fpu_get(void)
> {
> fpregs_lock();
> @@ -205,8 +260,29 @@ static inline void kvm_write_mmx_reg(int reg, const u64 *data)
> }
>
> #ifdef CONFIG_X86_64
> -static inline unsigned long kvm_read_egpr(int reg) { return 0; }
> -static inline void kvm_write_egpr(int reg, unsigned long data) { }
> +static inline unsigned long kvm_read_egpr(int reg)
> +{
> + unsigned long data;
> +
> + if (WARN_ON_ONCE(!cpu_has_xfeatures(XFEATURE_MASK_APX, NULL)))
> + return 0;
> +
> + kvm_fpu_get();
> + _kvm_read_egpr(reg, &data);
> + kvm_fpu_put();
> +
> + return data;
> +}
> +
> +static inline void kvm_write_egpr(int reg, unsigned long data)
> +{
> + if (WARN_ON_ONCE(!cpu_has_xfeatures(XFEATURE_MASK_APX, NULL)))
> + return;
> +
> + kvm_fpu_get();
> + _kvm_write_egpr(reg, &data);
> + kvm_fpu_put();
> +}
> #endif
>
> #endif