[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: Remaining MSR wrinkles
- To: Jan Beulich <jbeulich@xxxxxxxx>, Ian Jackson <iwj@xxxxxxxxxxxxxx>, Roger Pau Monné <roger.pau@xxxxxxxxxx>
- From: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
- Date: Thu, 11 Mar 2021 13:22:42 -0500
- Arc-authentication-results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=oracle.com; dmarc=pass action=none header.from=oracle.com; dkim=pass header.d=oracle.com; arc=none
- Arc-message-signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector9901; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=T+KFszDK3IGw1hvZbM6oiEBYTY7rKXeRV+C7FukvB+A=; b=Lxi4U8yyZ0IqcT93PGKcauVuCBeN4Eac7h6ow/GXOMvOMxdtUqqt+9XGQSDGlw7QQNEEbPKUzOCDsPb/MDW51wmbrCnKZ15ckKIWaLzRk876YznStQqi6zwaqI1MMvG3Wq6TlFmxuWQ8N9VviVRi8cnMnMnwLnpM6mMyx5D+vqezSTlJ3lMKgW6kfhDaUMfKeRNm3LpBJJf+VgyDHhJWgWF+j1HQkhGlIUi41j5V1CUKWTMxAdJ94ck4Hl7pxxnNFZTQOsErBHGRTDAKSNG5GP255AfDrU6LmeN0vmK7zTticaGqx951ng/81Gh+I5g0hCPyb8+q7WXWyxz/zQjwEw==
- Arc-seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=mWaFYBRG/0u8xMXr4Fz8jx8BVPM0X68NrgErrycb5cfL/0M6Y5ASAXEoh4166qKMs6xvhS95Ec1EkyddeX3VO1eHqwtdhH2WEZE75UVe/7rWv7spjMgBm69vHfUyIaZBUoOHNfsoBIMWjPgL3Kwkn6c9NcPmcLpTOoYVM8JAKHY/ERR89cOVxsyo8vnUYAc0qi6bK6ygT1NQAR1IreJxh9aYN3VtVPTJt+lx31Ip+3WajyogS/SpU/j2SvAxhJsW+WYtjgJAZmAjDTtveqnsW6S81nf3/KH4dfSMOrUf9CTRtU9zUUyecHIIV68qY5ZBglU/W16k2dnRIsFoZF5ZSg==
- Authentication-results: lists.xenproject.org; dkim=none (message not signed) header.d=none;lists.xenproject.org; dmarc=none action=none header.from=oracle.com;
- Cc: committers@xxxxxxxxxxxxxx, Andrew Cooper <andrew.cooper3@xxxxxxxxxx>, "xen-devel@xxxxxxxxxxxxxxxxxxxx" <xen-devel@xxxxxxxxxxxxxxxxxxxx>
- Delivery-date: Thu, 11 Mar 2021 18:23:18 +0000
- List-id: Xen developer discussion <xen-devel.lists.xenproject.org>
On 3/11/21 2:55 AM, Jan Beulich wrote:
> On 10.03.2021 20:09, Ian Jackson wrote:
>> (I bounced Roger's original mail to xen-devel. I hope it made it...)
>>
>> Roger Pau Monné writes ("Remaining MSR wrinkles"):
>>
>>> 2. RAPL_POWER_LIMIT: handle the MSR explicitly to make Solaris happy.
>>> Alternatively we can list in the release notes that Solaris guests
>>> require
>>> msr_relaxed=1. Andrew is working on a patch for this.
MSR_RAPL_POWER_UNIT (in Linux parlance), i.e. 0x606.
>> I would prefer to handle the MSR explicitly, for the same
>> compatibility reason as above.
> The question is here - we aren't sure yet that this is the only
> one, are we? Andrew suspects if this one MSR gets accessed this
> way, then likely others will be, too. Boris, can you tell for sure
> either way?
The only one that Solaris reads on boot in 0x606. However, a few more may be
accessed unguarded if kstat runs, as I mentioned in
https://lore.kernel.org/xen-devel/4fc3532b-f53f-2a15-ce64-f857816b0566@xxxxxxxxxx/
(I have not been able to empirically verify that)
>
> Also, Boris - any chance you could give your Tested-by for Roger's
> patch? It's otherwise ready to go in, but I'd prefer to commit it
> knowing that you've tested this hopefully final version. I'm sorry
> for the recurring requests to test this workaround.
For v5:
Tested-by: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
|
