diff mbox series

[RFC,15/19] kvm: handle KVM_EXIT_MEMORY_FAULT

Message ID 20230731162201.271114-16-xiaoyao.li@intel.com
State New
Headers show
Series QEMU gmem implemention | expand

Commit Message

Xiaoyao Li July 31, 2023, 4:21 p.m. UTC 
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
gmem memory backend.

Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
---
 accel/kvm/kvm-all.c | 52 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

Comments

Isaku Yamahata Aug. 2, 2023, 10:25 p.m. UTC | #1 
On Mon, Jul 31, 2023 at 12:21:57PM -0400,
Xiaoyao Li <xiaoyao.li@intel.com> 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
> gmem memory backend.
> 
> Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
> Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
> ---
>  accel/kvm/kvm-all.c | 52 +++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 52 insertions(+)
> 
> diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
> index f9b5050b8885..72d50b923bf2 100644
> --- a/accel/kvm/kvm-all.c
> +++ b/accel/kvm/kvm-all.c
> @@ -3040,6 +3040,48 @@ 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;
> +    void *addr;
> +    RAMBlock *rb;
> +    ram_addr_t offset;
> +    int ret = -1;
> +
> +    section = memory_region_find(get_system_memory(), start, size);
> +    if (!section.mr) {
> +        return ret;
> +    }
> +
> +    if (memory_region_can_be_private(section.mr)) {
> +        if (to_private) {
> +            ret = kvm_set_memory_attributes_private(start, size);
> +        } else {
> +            ret = kvm_set_memory_attributes_shared(start, size);
> +        }
> +
> +        if (ret) {
> +            return ret;
> +        }
> +
> +        addr = memory_region_get_ram_ptr(section.mr) +
> +               section.offset_within_region;
> +        rb = qemu_ram_block_from_host(addr, false, &offset);

Here we have already section. section.mr->ram_block.  We don't have to
scan the existing RAMBlocks.

Except that, looks good to me.
Reviewed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Xu Yilun Aug. 9, 2023, 3:02 p.m. UTC | #2 
On 2023-07-31 at 12:21:57 -0400, 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
> gmem memory backend.
> 
> Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
> Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
> ---
>  accel/kvm/kvm-all.c | 52 +++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 52 insertions(+)
> 
> diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
> index f9b5050b8885..72d50b923bf2 100644
> --- a/accel/kvm/kvm-all.c
> +++ b/accel/kvm/kvm-all.c
> @@ -3040,6 +3040,48 @@ 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;
> +    void *addr;
> +    RAMBlock *rb;
> +    ram_addr_t offset;
> +    int ret = -1;
> +
> +    section = memory_region_find(get_system_memory(), start, size);
> +    if (!section.mr) {
> +        return ret;
> +    }
> +
> +    if (memory_region_can_be_private(section.mr)) {
> +        if (to_private) {
> +            ret = kvm_set_memory_attributes_private(start, size);
> +        } else {
> +            ret = kvm_set_memory_attributes_shared(start, size);
> +        }
> +
> +        if (ret) {
> +            return ret;

Should we unref the memory region before return?

Thanks,
Yilun

> +        }
> +
> +        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");
> +    }
> +
> +    memory_region_unref(section.mr);
> +    return ret;
> +}
Xiaoyao Li Sept. 13, 2023, 6:59 a.m. UTC | #3 
On 8/3/2023 6:25 AM, Isaku Yamahata wrote:
> On Mon, Jul 31, 2023 at 12:21:57PM -0400,
> Xiaoyao Li <xiaoyao.li@intel.com> 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
>> gmem memory backend.
>>
>> Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
>> Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
>> ---
>>   accel/kvm/kvm-all.c | 52 +++++++++++++++++++++++++++++++++++++++++++++
>>   1 file changed, 52 insertions(+)
>>
>> diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
>> index f9b5050b8885..72d50b923bf2 100644
>> --- a/accel/kvm/kvm-all.c
>> +++ b/accel/kvm/kvm-all.c
>> @@ -3040,6 +3040,48 @@ 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;
>> +    void *addr;
>> +    RAMBlock *rb;
>> +    ram_addr_t offset;
>> +    int ret = -1;
>> +
>> +    section = memory_region_find(get_system_memory(), start, size);
>> +    if (!section.mr) {
>> +        return ret;
>> +    }
>> +
>> +    if (memory_region_can_be_private(section.mr)) {
>> +        if (to_private) {
>> +            ret = kvm_set_memory_attributes_private(start, size);
>> +        } else {
>> +            ret = kvm_set_memory_attributes_shared(start, size);
>> +        }
>> +
>> +        if (ret) {
>> +            return ret;
>> +        }
>> +
>> +        addr = memory_region_get_ram_ptr(section.mr) +
>> +               section.offset_within_region;
>> +        rb = qemu_ram_block_from_host(addr, false, &offset);
> 
> Here we have already section. section.mr->ram_block.  We don't have to
> scan the existing RAMBlocks.

But we don't have the @offset, do we?

> Except that, looks good to me.
> Reviewed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Xiaoyao Li Sept. 13, 2023, 7 a.m. UTC | #4 
On 8/9/2023 11:02 PM, Xu Yilun wrote:
> On 2023-07-31 at 12:21:57 -0400, 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
>> gmem memory backend.
>>
>> Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
>> Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
>> ---
>>   accel/kvm/kvm-all.c | 52 +++++++++++++++++++++++++++++++++++++++++++++
>>   1 file changed, 52 insertions(+)
>>
>> diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
>> index f9b5050b8885..72d50b923bf2 100644
>> --- a/accel/kvm/kvm-all.c
>> +++ b/accel/kvm/kvm-all.c
>> @@ -3040,6 +3040,48 @@ 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;
>> +    void *addr;
>> +    RAMBlock *rb;
>> +    ram_addr_t offset;
>> +    int ret = -1;
>> +
>> +    section = memory_region_find(get_system_memory(), start, size);
>> +    if (!section.mr) {
>> +        return ret;
>> +    }
>> +
>> +    if (memory_region_can_be_private(section.mr)) {
>> +        if (to_private) {
>> +            ret = kvm_set_memory_attributes_private(start, size);
>> +        } else {
>> +            ret = kvm_set_memory_attributes_shared(start, size);
>> +        }
>> +
>> +        if (ret) {
>> +            return ret;
> 
> Should we unref the memory region before return?

Thanks for catching this!

> Thanks,
> Yilun
> 
>> +        }
>> +
>> +        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");
>> +    }
>> +
>> +    memory_region_unref(section.mr);
>> +    return ret;
>> +}
diff mbox series

Patch

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index f9b5050b8885..72d50b923bf2 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -3040,6 +3040,48 @@  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;
+    void *addr;
+    RAMBlock *rb;
+    ram_addr_t offset;
+    int ret = -1;
+
+    section = memory_region_find(get_system_memory(), start, size);
+    if (!section.mr) {
+        return ret;
+    }
+
+    if (memory_region_can_be_private(section.mr)) {
+        if (to_private) {
+            ret = kvm_set_memory_attributes_private(start, size);
+        } else {
+            ret = kvm_set_memory_attributes_shared(start, size);
+        }
+
+        if (ret) {
+            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");
+    }
+
+    memory_region_unref(section.mr);
+    return ret;
+}
+
 int kvm_cpu_exec(CPUState *cpu)
 {
     struct kvm_run *run = cpu->kvm_run;
@@ -3198,6 +3240,16 @@  int kvm_cpu_exec(CPUState *cpu)
                 break;
             }
             break;
+        case KVM_EXIT_MEMORY_FAULT:
+            if (run->memory.flags & ~KVM_MEMORY_EXIT_FLAG_PRIVATE) {
+                error_report("KVM_EXIT_MEMORY_FAULT: Unknown flag 0x%" PRIx64,
+                             (uint64_t)run->memory.flags);
+                ret = -1;
+                break;
+            }
+            ret = kvm_convert_memory(run->memory.gpa, run->memory.size,
+                                     run->memory.flags & KVM_MEMORY_EXIT_FLAG_PRIVATE);
+            break;
         default:
             DPRINTF("kvm_arch_handle_exit\n");
             ret = kvm_arch_handle_exit(cpu, run);