The original code is essentially asking: for each possible floating point mode, ask if reg_num is a status control register or a data register. It is redundant to ask those same questions for every possible floating point mode case. In order to only ask the "status control register or data register" question once, the variables in the status control if statement and the data register if statement that would be different depending on the type of floating point mode (for example, KVM_REG_RISCV_FP_F_REG(fcsr) would be KVM_REG_RISCV_FP_D_REG(fcsr) if the floating point mode was double) were made local variables of the entire function so that once the cpu passes the if statement inquiring whether it is double point mode or single point mode, all the variables that change depending on the type in the status control if statements and data register if statements will be set to the appropriate values they should be when in that mode before/when it enters the status control and data register if statements, allowing me to only have to ask those questions once and creating a dynamic code that changes based on the information. This results in a "asking the type then asking status control or data register question once" structure rather than a type-questions, type-questions redundant structure like before. This results in faster cpu execution because despite the longer lines of code the cpu has to make less decisions, which saves time in case, due to its tendency to make assumptions about what an if statement will evaluate to, it has to backpedal because it realized it needed to go down a different if statement/path. Finding an address via my bare-metal approach is also faster than looking up an object properties and then an array. It is also more maintainable in the future. If the original code needed to be changed, you would have to remember to do the same thing to both type blocks whereas mine would just require a change in the beginning if statements. If a new floating point mode was added you have to ask those same questions all over again, which may make the code longer in the long run. I also renamed reg_num to token_reg_num in my code as I felt it made it clearer that it was the register number the application wants and requested in a token. It differentiated it from the many other variables with the word reg in it. Signed-off-by: Paul White --- arch/riscv/kvm/vcpu_fp.c | 70 +++++++++++++++++++++++----------------- 1 file changed, 41 insertions(+), 29 deletions(-) diff --git a/arch/riscv/kvm/vcpu_fp.c b/arch/riscv/kvm/vcpu_fp.c index bb11e6757d34..16999a5c45de 100644 --- a/arch/riscv/kvm/vcpu_fp.c +++ b/arch/riscv/kvm/vcpu_fp.c @@ -83,41 +83,53 @@ int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu, struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; unsigned long __user *uaddr = (unsigned long __user *)(unsigned long)reg->addr; - unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + unsigned long token_reg_num = reg->id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | rtype); void *reg_val; + u32 *fcsr_addr; + void *f_array_addr; + size_t byte_offset = 0; + unsigned long offical_fcsr_num = 0; + unsigned long offical_first_reg = 0; + unsigned long offical_last_reg = 0; + if ((rtype == KVM_REG_RISCV_FP_F) && riscv_isa_extension_available(vcpu->arch.isa, F)) { + fcsr_addr = &cntx->fp.f.fcsr; + f_array_addr = &cntx->fp.f.f; + byte_offset = 4; + offical_fcsr_num = KVM_REG_RISCV_FP_F_REG(fcsr); + offical_first_reg = KVM_REG_RISCV_FP_F_REG(f[0]); + offical_last_reg = KVM_REG_RISCV_FP_F_REG(f[31]); + } else if ((rtype == KVM_REG_RISCV_FP_D) && + riscv_isa_extension_available(vcpu->arch.isa, D)) { + fcsr_addr = &cntx->fp.d.fcsr; + f_array_addr = &cntx->fp.d.f; + byte_offset = 8; + offical_fcsr_num = KVM_REG_RISCV_FP_D_REG(fcsr); + offical_first_reg = KVM_REG_RISCV_FP_D_REG(f[0]); + offical_last_reg = KVM_REG_RISCV_FP_D_REG(f[31]); + } else { + return -ENOENT; + } + + if (token_reg_num == offical_fcsr_num) { if (KVM_REG_SIZE(reg->id) != sizeof(u32)) return -EINVAL; - if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr)) - reg_val = &cntx->fp.f.fcsr; - else if ((KVM_REG_RISCV_FP_F_REG(f[0]) <= reg_num) && - reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) { - reg_num = array_index_nospec(reg_num, - ARRAY_SIZE(cntx->fp.f.f)); - reg_val = &cntx->fp.f.f[reg_num]; - } else - return -ENOENT; - } else if ((rtype == KVM_REG_RISCV_FP_D) && - riscv_isa_extension_available(vcpu->arch.isa, D)) { - if (reg_num == KVM_REG_RISCV_FP_D_REG(fcsr)) { - if (KVM_REG_SIZE(reg->id) != sizeof(u32)) - return -EINVAL; - reg_val = &cntx->fp.d.fcsr; - } else if ((KVM_REG_RISCV_FP_D_REG(f[0]) <= reg_num) && - reg_num <= KVM_REG_RISCV_FP_D_REG(f[31])) { - if (KVM_REG_SIZE(reg->id) != sizeof(u64)) - return -EINVAL; - reg_num = array_index_nospec(reg_num, - ARRAY_SIZE(cntx->fp.d.f)); - reg_val = &cntx->fp.d.f[reg_num]; - } else - return -ENOENT; - } else + reg_val = fcsr_addr; + } else if ((offical_first_reg <= token_reg_num) && (token_reg_num <= offical_last_reg)) { + if ((KVM_REG_SIZE(reg->id) != sizeof(u32)) && + (KVM_REG_SIZE(reg->id) != sizeof(u64))) { + return -EINVAL; + } + token_reg_num = array_index_nospec(token_reg_num, + 32); + reg_val = (u8 *)f_array_addr + (token_reg_num * byte_offset); + } else { return -ENOENT; + } if (copy_to_user(uaddr, reg_val, KVM_REG_SIZE(reg->id))) return -EFAULT; @@ -144,9 +156,9 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu, if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr)) reg_val = &cntx->fp.f.fcsr; else if ((KVM_REG_RISCV_FP_F_REG(f[0]) <= reg_num) && - reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) { + reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) { reg_num = array_index_nospec(reg_num, - ARRAY_SIZE(cntx->fp.f.f)); + ARRAY_SIZE(cntx->fp.f.f)); reg_val = &cntx->fp.f.f[reg_num]; } else return -ENOENT; @@ -161,7 +173,7 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu, if (KVM_REG_SIZE(reg->id) != sizeof(u64)) return -EINVAL; reg_num = array_index_nospec(reg_num, - ARRAY_SIZE(cntx->fp.d.f)); + ARRAY_SIZE(cntx->fp.d.f)); reg_val = &cntx->fp.d.f[reg_num]; } else return -ENOENT; -- 2.53.0