| 1 |
On 01/12/2018 12:42 PM, Mick wrote: |
| 2 |
> On Friday, 12 January 2018 17:47:46 GMT Rich Freeman wrote: |
| 3 |
>> On Fri, Jan 12, 2018 at 11:23 AM, Corbin Bird <corbinbird@×××××××.net> |
| 4 |
> wrote: |
| 5 |
>>> On 01/11/2018 05:02 PM, Rich Freeman wrote: |
| 6 |
>>>> IMO Spectre is going to drive some microcode updates for relatively |
| 7 |
>>>> recent CPUs, compiler improvements, and some hand-tuning of |
| 8 |
>>>> particularly critical code. |
| 9 |
>>> The microcode updates pushed out for AMD by Gentoo seem to be only for : |
| 10 |
>>> Fam16h, Fam17h CPUs. |
| 11 |
>> FWIW even the 17h microcode doesn't seem to be updating on my Ryzen: |
| 12 |
>> |
| 13 |
>> dmesg | grep microco |
| 14 |
>> [ 0.989279] microcode: CPU0: patch_level=0x08001129 |
| 15 |
>> [ 0.989421] microcode: CPU1: patch_level=0x08001129 |
| 16 |
>> [ 0.989565] microcode: CPU2: patch_level=0x08001129 |
| 17 |
>> [ 0.989708] microcode: CPU3: patch_level=0x08001129 |
| 18 |
>> [ 0.989857] microcode: CPU4: patch_level=0x08001129 |
| 19 |
>> [ 0.990001] microcode: CPU5: patch_level=0x08001129 |
| 20 |
>> [ 0.990183] microcode: CPU6: patch_level=0x08001129 |
| 21 |
>> [ 0.990332] microcode: CPU7: patch_level=0x08001129 |
| 22 |
>> [ 0.990475] microcode: CPU8: patch_level=0x08001129 |
| 23 |
>> [ 0.990619] microcode: CPU9: patch_level=0x08001129 |
| 24 |
>> [ 0.990764] microcode: CPU10: patch_level=0x08001129 |
| 25 |
>> [ 0.990905] microcode: CPU11: patch_level=0x08001129 |
| 26 |
>> [ 0.991095] microcode: Microcode Update Driver: v2.2. |
| 27 |
> My AMD: |
| 28 |
> |
| 29 |
> [ 0.025000] smpboot: CPU0: AMD A10-7850K Radeon R7, 12 Compute Cores 4C+8G |
| 30 |
> (family: 0x15, model: 0x30, stepping: 0x1) |
| 31 |
> |
| 32 |
> is similarly failing to show signs of early microcode update, as it always |
| 33 |
> did: |
| 34 |
> |
| 35 |
> $ dmesg | grep -i microcode |
| 36 |
> [ 1.348991] microcode: CPU0: patch_level=0x06003106 |
| 37 |
> [ 1.349718] microcode: CPU1: patch_level=0x06003106 |
| 38 |
> [ 1.350434] microcode: CPU2: patch_level=0x06003106 |
| 39 |
> [ 1.351158] microcode: CPU3: patch_level=0x06003106 |
| 40 |
> [ 1.351879] microcode: Microcode Update Driver: v2.2. |
| 41 |
> |
| 42 |
> |
| 43 |
>> That said, there still isn't any AMD documentation around the |
| 44 |
>> microcode updates that I've been able to find, so I have no idea what |
| 45 |
>> the correct patch level is even supposed to be. I just know that I'm |
| 46 |
>> not getting a message about early updates. I do have linux 4.4.13 |
| 47 |
>> which includes the family 17h patch. |
| 48 |
> I'm on 4.14.12-gentoo now. |
| 49 |
> |
| 50 |
> |
| 51 |
>> The other odd thing is that a firmware update was released for my |
| 52 |
>> motherboard (ASRock AB350 Pro4) on the 10th, and if I flash it grub |
| 53 |
>> will no longer boot the linux kernel, and it is pretty slow overall, |
| 54 |
>> but it will still boot memtestx86 just fine. I figured I'd wait a few |
| 55 |
>> days and see if there is any further info on it. |
| 56 |
> No Asus MoBo firmware updates here ... but would they be even required/ |
| 57 |
> necessary for the CPU bugs? |
| 58 |
|
| 59 |
In the old days, Windows / DOS, did not have any "microcode update |
| 60 |
loader". For those old versions of Windows / DOS, an updated BIOS was |
| 61 |
the only way to update the CPU microcode. |
| 62 |
|
| 63 |
I have seen something calling itself the "microcode update loader" in |
| 64 |
Win 7 x64. Have no idea what it is really doing. |
| 65 |
|
| 66 |
------- |
| 67 |
|
| 68 |
The Fam16h and Fam17h microcode updates were new to Gentoo? |
| 69 |
I don't recall ever seeing them before. |
| 70 |
|
| 71 |
Corbin |
Archives