Re: [PATCH v3 10/70] kvm: handle KVM_EXIT_MEMORY_FAULT

[Xiaoyao Li <xiaoyao.li@intel.com>]

On 11/15/2023 6:42 PM, Daniel P. Berrangé wrote:
> On Wed, Nov 15, 2023 at 02:14:19AM -0500, Xiaoyao Li wrote:
>> From: Chao Peng <chao.p.peng@linux.intel.com>
>>
>> Currently only KVM_MEMORY_EXIT_FLAG_PRIVATE in flags is valid when
>> KVM_EXIT_MEMORY_FAULT happens. It indicates userspace needs to do
>> the memory conversion on the RAMBlock to turn the memory into desired
>> attribute, i.e., private/shared.
>>
>> Note, KVM_EXIT_MEMORY_FAULT makes sense only when the RAMBlock has
>> guest_memfd memory backend.
>>
>> Note, KVM_EXIT_MEMORY_FAULT returns with -EFAULT, so special handling is
>> added.
>>
>> Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
>> Co-developed-by: Xiaoyao Li <xiaoyao.li@intel.com>
>> Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
>> ---
>>   accel/kvm/kvm-all.c | 76 +++++++++++++++++++++++++++++++++++++++------
>>   1 file changed, 66 insertions(+), 10 deletions(-)
>>
>> diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
>> index 76e2404d54d2..58abbcb6926e 100644
>> --- a/accel/kvm/kvm-all.c
>> +++ b/accel/kvm/kvm-all.c
>> @@ -2902,6 +2902,50 @@ static void kvm_eat_signals(CPUState *cpu)
>>       } while (sigismember(&chkset, SIG_IPI));
>>   }
>>   
>> +static int kvm_convert_memory(hwaddr start, hwaddr size, bool to_private)
>> +{
>> +    MemoryRegionSection section;
>> +    ram_addr_t offset;
>> +    RAMBlock *rb;
>> +    void *addr;
>> +    int ret = -1;
>> +
>> +    section = memory_region_find(get_system_memory(), start, size);
>> +    if (!section.mr) {
>> +        return ret;
>> +    }
>> +
>> +    if (memory_region_has_guest_memfd(section.mr)) {
>> +        if (to_private) {
>> +            ret = kvm_set_memory_attributes_private(start, size);
>> +        } else {
>> +            ret = kvm_set_memory_attributes_shared(start, size);
>> +        }
>> +
>> +        if (ret) {
>> +            memory_region_unref(section.mr);
>> +            return ret;
>> +        }
>> +
>> +        addr = memory_region_get_ram_ptr(section.mr) +
>> +               section.offset_within_region;
>> +        rb = qemu_ram_block_from_host(addr, false, &offset);
>> +        /*
>> +         * With KVM_SET_MEMORY_ATTRIBUTES by kvm_set_memory_attributes(),
>> +         * operation on underlying file descriptor is only for releasing
>> +         * unnecessary pages.
>> +         */
>> +        ram_block_convert_range(rb, offset, size, to_private);
>> +    } else {
>> +        warn_report("Convert non guest_memfd backed memory region "
>> +                    "(0x%"HWADDR_PRIx" ,+ 0x%"HWADDR_PRIx") to %s",
>> +                    start, size, to_private ? "private" : "shared");
> 
> Again, if you're returning '-1' to indicate error, then
> using warn_report is wrong, it should be error_report.
> 
> warn_report is for when you return success, indicating
> the problem was non-fatal.

Learned.

Thanks!

>> +    }
>> +
>> +    memory_region_unref(section.mr);
>> +    return ret;
>> +}
>> +
>>   int kvm_cpu_exec(CPUState *cpu)
>>   {
>>       struct kvm_run *run = cpu->kvm_run;
>> @@ -2969,18 +3013,20 @@ int kvm_cpu_exec(CPUState *cpu)
>>                   ret = EXCP_INTERRUPT;
>>                   break;
>>               }
>> -            fprintf(stderr, "error: kvm run failed %s\n",
>> -                    strerror(-run_ret));
>> +            if (!(run_ret == -EFAULT && run->exit_reason == KVM_EXIT_MEMORY_FAULT)) {
>> +                fprintf(stderr, "error: kvm run failed %s\n",
>> +                        strerror(-run_ret));
>>   #ifdef TARGET_PPC
>> -            if (run_ret == -EBUSY) {
>> -                fprintf(stderr,
>> -                        "This is probably because your SMT is enabled.\n"
>> -                        "VCPU can only run on primary threads with all "
>> -                        "secondary threads offline.\n");
>> -            }
>> +                if (run_ret == -EBUSY) {
>> +                    fprintf(stderr,
>> +                            "This is probably because your SMT is enabled.\n"
>> +                            "VCPU can only run on primary threads with all "
>> +                            "secondary threads offline.\n");
>> +                }
>>   #endif
>> -            ret = -1;
>> -            break;
>> +                ret = -1;
>> +                break;
>> +            }
>>           }
>>   
>>           trace_kvm_run_exit(cpu->cpu_index, run->exit_reason);
>> @@ -3067,6 +3113,16 @@ int kvm_cpu_exec(CPUState *cpu)
>>                   break;
>>               }
>>               break;
>> +        case KVM_EXIT_MEMORY_FAULT:
>> +            if (run->memory_fault.flags & ~KVM_MEMORY_EXIT_FLAG_PRIVATE) {
>> +                error_report("KVM_EXIT_MEMORY_FAULT: Unknown flag 0x%" PRIx64,
>> +                             (uint64_t)run->memory_fault.flags);
>> +                ret = -1;
>> +                break;
>> +            }
>> +            ret = kvm_convert_memory(run->memory_fault.gpa, run->memory_fault.size,
>> +                                     run->memory_fault.flags & KVM_MEMORY_EXIT_FLAG_PRIVATE);
>> +            break;
>>           default:
>>               DPRINTF("kvm_arch_handle_exit\n");
>>               ret = kvm_arch_handle_exit(cpu, run);
>> -- 
>> 2.34.1
>>
> 
> With regards,
> Daniel