From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from baidu.com (mx24.baidu.com [111.206.215.185]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 012D73A8EF for ; Thu, 18 Apr 2024 07:10:05 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=111.206.215.185 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1713424209; cv=none; b=FvbtzrU6IfPCaMffR85IZIItF7qLU8MtxKpRguYFk54Wr/axgEXuvxSGzUerSq3fORm9P+lGd/c9uqHLCZx3qE7gRjj8Zb417nJOmxCkzkXTDtbEtgCwlSvITGYMwApvsOenwx9/7ZgHT5UuH9W95htRGxGIpmyugkmW8pjbejU= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1713424209; c=relaxed/simple; bh=rEeZyMyRdetZw0digCbVNJOeb3XjA7vXXUxfllL4rMw=; h=From:To:CC:Subject:Date:Message-ID:References:In-Reply-To: Content-Type:MIME-Version; b=msiRWqzu/+4pkqY5d0MKNnu+o+4Z/0CumZuT/og/oRRPgyTfxTIb9o6/fF/bMDW7PHNnXvWo/PwYcIBb8Wx8Y9wYnY60Z9cNiKZnzbD61LfoiANmNs32foHnqvt5/PogQTQ8r0Ku2j0dgY8knZVGTIsOY9nRj8r/Q0CzF/Y8U7k= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=baidu.com; spf=pass smtp.mailfrom=baidu.com; arc=none smtp.client-ip=111.206.215.185 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=baidu.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=baidu.com From: "Li,Rongqing" To: Marc Zyngier CC: "oliver.upton@linux.dev" , "james.morse@arm.com" , "suzuki.poulose@arm.com" , "yuzenghui@huawei.com" , "catalin.marinas@arm.com" , "will@kernel.org" , "linux-arm-kernel@lists.infradead.org" , "kvmarm@lists.linux.dev" Subject: RE: [PATCH] KVM: arm64: Consider NUMA affinity when allocating per-CPU stack_page Thread-Topic: [PATCH] KVM: arm64: Consider NUMA affinity when allocating per-CPU stack_page Thread-Index: AQHajuYSEQnMbfiDFkC1SUvVaEYWGLFoa0cAgAUw1aA= Date: Thu, 18 Apr 2024 06:53:58 +0000 Message-ID: References: <20240415033614.43518-1-lirongqing@baidu.com> <86bk6brsb5.wl-maz@kernel.org> In-Reply-To: <86bk6brsb5.wl-maz@kernel.org> Accept-Language: zh-CN, en-US Content-Language: zh-CN X-MS-Has-Attach: X-MS-TNEF-Correlator: x-baidu-bdmsfe-datecheck: 1_BJHW-Mail-Ex15_2024-04-18 14:53:58:552 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Precedence: bulk X-Mailing-List: kvmarm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-FEAS-Client-IP: 10.127.64.38 X-FE-Last-Public-Client-IP: 100.100.100.38 X-FE-Policy-ID: 15:10:21:SYSTEM > Li RongQing wrote: > > > > per-CPU stack_page are dominantly accessed from their own local CPUs, > > so allocate them node-local to improve performance. >=20 > Do you have any performance data to back this up? >=20 > Given that this is only used in the non-VHE case, and that by doing so yo= u have > left quite a lot of performance on the floor already, I'm even more surpr= ised to > see the performance argument. >=20 Sorry, I have not setup to test it. > Furthermore, you don't address the allocation of per-CPU data, which has = a > much larger potential impact, given how the HYP code is structured. >=20 I will add it in V2 Thanks -LiRongQing