From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.18]) (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 EEC5322578C; Fri, 15 Aug 2025 14:31:40 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=198.175.65.18 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1755268302; cv=none; b=NNRhDB8/kHrRVdHDIAp/8xUt+33BzF0I5ppGX1DyHVc/lMyjgaWqIa2F3H73DorE+weOvs8QwDYmynTOSsnVJWCSJ8y4L2hZEpAbDHXtUzH1ZNLz7bno0vGsiCFbdyEaW4zOEyrQKk5rqIfl/aFJ6haXAMlG6Px8uoRau9CGAlE= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1755268302; c=relaxed/simple; bh=0eZhTbtkEW/g83dukhSn7IpMHxDzJ8OUw0DnpseI99s=; h=Message-ID:Date:MIME-Version:Subject:To:Cc:References:From: In-Reply-To:Content-Type; b=e66Y1hto15HtI/SPSFV61AQHkZ322uFzt1Z/qUhO3ViHXfxF4ZxAcNo+F+1Q67jVoM1RPtbnlJrcXqCG9CeXUGDHIjj9QoNSg4uqhM9IPEWU8W7IJIW1oScqtnBrCnRMu4f6zqFf32jtYpBvfSrq6ph1JZmt7TUTnMGQA2ph8dc= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com; spf=pass smtp.mailfrom=intel.com; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b=n4cv0a2l; arc=none smtp.client-ip=198.175.65.18 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=intel.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=intel.com header.i=@intel.com header.b="n4cv0a2l" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1755268301; x=1786804301; h=message-id:date:mime-version:subject:to:cc:references: from:in-reply-to:content-transfer-encoding; bh=0eZhTbtkEW/g83dukhSn7IpMHxDzJ8OUw0DnpseI99s=; b=n4cv0a2l1AHIeFkE8s31vP1kcyb++tSg9nLfzTi5dd5NGbJMv9+WMG3i 2cMXSJ0/IKX5oqeYhH9Yf6ZZN1GYbWZfUGEOzRi31ARm0pP+sWyZtAq9f UZC5GoTPnyWiGp85jykFZIp1GCdHqLQb94vLMMkQYIBqy4yShZPjA03bg TEWKN1VdkL25OMRMn8qeA+Rx+RmsQr8L0+klEfAVQwoZHUZUWwV+lDpyQ 5aZOeRg10xGKntb5C1avMGFJ6Yna/95/RrmBMa2d/E1vEt+FZFtRAS75Q 967hxfnkouJJbcDyT2MZE4iiAchV67NMDu4CEjQVLWeZbJfI2OGBs6OXe w==; X-CSE-ConnectionGUID: SR3Npxk0T6WEQhd87oFsVQ== X-CSE-MsgGUID: 398FdSQZT5Cd2pAWE73yVg== X-IronPort-AV: E=McAfee;i="6800,10657,11523"; a="57663162" X-IronPort-AV: E=Sophos;i="6.17,290,1747724400"; d="scan'208";a="57663162" Received: from orviesa002.jf.intel.com ([10.64.159.142]) by orvoesa110.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 15 Aug 2025 07:31:41 -0700 X-CSE-ConnectionGUID: xQbTjg6KQKqihLGa+2xmZQ== X-CSE-MsgGUID: 6USf6956RjuKh+fJhpnDHg== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,290,1747724400"; d="scan'208";a="198017860" Received: from puneetse-mobl.amr.corp.intel.com (HELO [10.125.111.211]) ([10.125.111.211]) by orviesa002-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 15 Aug 2025 07:31:40 -0700 Message-ID: Date: Fri, 15 Aug 2025 07:31:39 -0700 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 User-Agent: Mozilla Thunderbird Subject: Re: [PATCH v3 1/1] iommu/sva: Invalidate KVA range on kernel TLB flush To: Baolu Lu , "Tian, Kevin" , Jason Gunthorpe Cc: Joerg Roedel , Will Deacon , Robin Murphy , Jann Horn , Vasant Hegde , Alistair Popple , Peter Zijlstra , Uladzislau Rezki , Jean-Philippe Brucker , Andy Lutomirski , "Lai, Yi1" , "iommu@lists.linux.dev" , "security@kernel.org" , "linux-kernel@vger.kernel.org" , "stable@vger.kernel.org" References: <20250806052505.3113108-1-baolu.lu@linux.intel.com> <20250806155223.GV184255@nvidia.com> <20250806160904.GX184255@nvidia.com> <62d21545-9e75-41e3-89a3-f21dda15bf16@intel.com> <4a8df0e8-bd5a-44e4-acce-46ba75594846@linux.intel.com> <20250807195154.GO184255@nvidia.com> <3f7a0524-75e1-447f-bdf5-db3f088a0ca9@linux.intel.com> From: Dave Hansen Content-Language: en-US Autocrypt: addr=dave.hansen@intel.com; keydata= xsFNBE6HMP0BEADIMA3XYkQfF3dwHlj58Yjsc4E5y5G67cfbt8dvaUq2fx1lR0K9h1bOI6fC oAiUXvGAOxPDsB/P6UEOISPpLl5IuYsSwAeZGkdQ5g6m1xq7AlDJQZddhr/1DC/nMVa/2BoY 2UnKuZuSBu7lgOE193+7Uks3416N2hTkyKUSNkduyoZ9F5twiBhxPJwPtn/wnch6n5RsoXsb ygOEDxLEsSk/7eyFycjE+btUtAWZtx+HseyaGfqkZK0Z9bT1lsaHecmB203xShwCPT49Blxz VOab8668QpaEOdLGhtvrVYVK7x4skyT3nGWcgDCl5/Vp3TWA4K+IofwvXzX2ON/Mj7aQwf5W iC+3nWC7q0uxKwwsddJ0Nu+dpA/UORQWa1NiAftEoSpk5+nUUi0WE+5DRm0H+TXKBWMGNCFn c6+EKg5zQaa8KqymHcOrSXNPmzJuXvDQ8uj2J8XuzCZfK4uy1+YdIr0yyEMI7mdh4KX50LO1 pmowEqDh7dLShTOif/7UtQYrzYq9cPnjU2ZW4qd5Qz2joSGTG9eCXLz5PRe5SqHxv6ljk8mb ApNuY7bOXO/A7T2j5RwXIlcmssqIjBcxsRRoIbpCwWWGjkYjzYCjgsNFL6rt4OL11OUF37wL QcTl7fbCGv53KfKPdYD5hcbguLKi/aCccJK18ZwNjFhqr4MliQARAQABzUVEYXZpZCBDaHJp c3RvcGhlciBIYW5zZW4gKEludGVsIFdvcmsgQWRkcmVzcykgPGRhdmUuaGFuc2VuQGludGVs LmNvbT7CwXgEEwECACIFAlQ+9J0CGwMGCwkIBwMCBhUIAgkKCwQWAgMBAh4BAheAAAoJEGg1 lTBwyZKwLZUP/0dnbhDc229u2u6WtK1s1cSd9WsflGXGagkR6liJ4um3XCfYWDHvIdkHYC1t MNcVHFBwmQkawxsYvgO8kXT3SaFZe4ISfB4K4CL2qp4JO+nJdlFUbZI7cz/Td9z8nHjMcWYF IQuTsWOLs/LBMTs+ANumibtw6UkiGVD3dfHJAOPNApjVr+M0P/lVmTeP8w0uVcd2syiaU5jB aht9CYATn+ytFGWZnBEEQFnqcibIaOrmoBLu2b3fKJEd8Jp7NHDSIdrvrMjYynmc6sZKUqH2 I1qOevaa8jUg7wlLJAWGfIqnu85kkqrVOkbNbk4TPub7VOqA6qG5GCNEIv6ZY7HLYd/vAkVY E8Plzq/NwLAuOWxvGrOl7OPuwVeR4hBDfcrNb990MFPpjGgACzAZyjdmYoMu8j3/MAEW4P0z F5+EYJAOZ+z212y1pchNNauehORXgjrNKsZwxwKpPY9qb84E3O9KYpwfATsqOoQ6tTgr+1BR CCwP712H+E9U5HJ0iibN/CDZFVPL1bRerHziuwuQuvE0qWg0+0SChFe9oq0KAwEkVs6ZDMB2 P16MieEEQ6StQRlvy2YBv80L1TMl3T90Bo1UUn6ARXEpcbFE0/aORH/jEXcRteb+vuik5UGY 5TsyLYdPur3TXm7XDBdmmyQVJjnJKYK9AQxj95KlXLVO38lczsFNBFRjzmoBEACyAxbvUEhd GDGNg0JhDdezyTdN8C9BFsdxyTLnSH31NRiyp1QtuxvcqGZjb2trDVuCbIzRrgMZLVgo3upr MIOx1CXEgmn23Zhh0EpdVHM8IKx9Z7V0r+rrpRWFE8/wQZngKYVi49PGoZj50ZEifEJ5qn/H Nsp2+Y+bTUjDdgWMATg9DiFMyv8fvoqgNsNyrrZTnSgoLzdxr89FGHZCoSoAK8gfgFHuO54B lI8QOfPDG9WDPJ66HCodjTlBEr/Cwq6GruxS5i2Y33YVqxvFvDa1tUtl+iJ2SWKS9kCai2DR 3BwVONJEYSDQaven/EHMlY1q8Vln3lGPsS11vSUK3QcNJjmrgYxH5KsVsf6PNRj9mp8Z1kIG qjRx08+nnyStWC0gZH6NrYyS9rpqH3j+hA2WcI7De51L4Rv9pFwzp161mvtc6eC/GxaiUGuH BNAVP0PY0fqvIC68p3rLIAW3f97uv4ce2RSQ7LbsPsimOeCo/5vgS6YQsj83E+AipPr09Caj 0hloj+hFoqiticNpmsxdWKoOsV0PftcQvBCCYuhKbZV9s5hjt9qn8CE86A5g5KqDf83Fxqm/ vXKgHNFHE5zgXGZnrmaf6resQzbvJHO0Fb0CcIohzrpPaL3YepcLDoCCgElGMGQjdCcSQ+Ci FCRl0Bvyj1YZUql+ZkptgGjikQARAQABwsFfBBgBAgAJBQJUY85qAhsMAAoJEGg1lTBwyZKw l4IQAIKHs/9po4spZDFyfDjunimEhVHqlUt7ggR1Hsl/tkvTSze8pI1P6dGp2XW6AnH1iayn yRcoyT0ZJ+Zmm4xAH1zqKjWplzqdb/dO28qk0bPso8+1oPO8oDhLm1+tY+cOvufXkBTm+whm +AyNTjaCRt6aSMnA/QHVGSJ8grrTJCoACVNhnXg/R0g90g8iV8Q+IBZyDkG0tBThaDdw1B2l asInUTeb9EiVfL/Zjdg5VWiF9LL7iS+9hTeVdR09vThQ/DhVbCNxVk+DtyBHsjOKifrVsYep WpRGBIAu3bK8eXtyvrw1igWTNs2wazJ71+0z2jMzbclKAyRHKU9JdN6Hkkgr2nPb561yjcB8 sIq1pFXKyO+nKy6SZYxOvHxCcjk2fkw6UmPU6/j/nQlj2lfOAgNVKuDLothIxzi8pndB8Jju KktE5HJqUUMXePkAYIxEQ0mMc8Po7tuXdejgPMwgP7x65xtfEqI0RuzbUioFltsp1jUaRwQZ MTsCeQDdjpgHsj+P2ZDeEKCbma4m6Ez/YWs4+zDm1X8uZDkZcfQlD9NldbKDJEXLIjYWo1PH hYepSffIWPyvBMBTW2W5FRjJ4vLRrJSUoEfJuPQ3vW9Y73foyo/qFoURHO48AinGPZ7PC7TF vUaNOTjKedrqHkaOcqB185ahG2had0xnFsDPlx5y In-Reply-To: <3f7a0524-75e1-447f-bdf5-db3f088a0ca9@linux.intel.com> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On 8/15/25 02:16, Baolu Lu wrote: > On 8/8/2025 10:57 AM, Tian, Kevin wrote: >> pud_free_pmd_page() >>     ... >>     for (i = 0; i < PTRS_PER_PMD; i++) { >>         if (!pmd_none(pmd_sv[i])) { >>             pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]); >>             pte_free_kernel(&init_mm, pte); >>         } >>     } >> >>     free_page((unsigned long)pmd_sv); >> >> Otherwise the risk still exists if the pmd page is repurposed before the >> pte work is scheduled. > > You're right that freeing high-level page table pages also requires an > IOTLB flush before the pages are freed. But I question the practical > risk of the race given the extremely small time window. I hear that Linux is gaining popularity these days. There might even be dozens of users! Given that large scale of dozens (or even hundreds??) of users, I would suggest exercising some care. The race might be small but it only needs to happen once to cause chaos. Seriously, though... A race is a race. Preemption or interrupts or SMIs or VMExits or a million other things can cause a "small time window" to become a big time window. Even perceived small races need to be fixed. > If this is a real concern, a potential mitigation would be to clear > the U/S bits in all page table entries for kernel address space? But > I am not confident in making that change at this time as I am unsure > of the side effects it might cause. That doesn't do any good. I even went as far as double-checking months ago with the IOMMU hardware folks to confirm the actual implementation. I'm really surprised this is being brought up again. >> another observation - pte_free_kernel is not used in remove_pagetable () >> and __change_page_attr(). Is it straightforward to put it in those paths >> or do we need duplicate some deferring logic there? > > The remove_pagetable() function is called in the path where memory is > hot-removed from the system, right? No. Not right. This is in the vmalloc() code: the side of things that _creates_ mappings for new allocations, not tears them down.