From: Thomas Gleixner <tglx@linutronix.de> To: "Jacob Pan \(Jun\)" <jacob.jun.pan@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com>, Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>, H Peter Anvin <hpa@zytor.com>, David Woodhouse <dwmw2@infradead.org>, Lu Baolu <baolu.lu@linux.intel.com>, Dave Hansen <dave.hansen@intel.com>, Tony Luck <tony.luck@intel.com>, Ashok Raj <ashok.raj@intel.com>, Dave Jiang <dave.jiang@intel.com>, Sohil Mehta <sohil.mehta@intel.com>, Ravi V Shankar <ravi.v.shankar@intel.com>, linux-kernel <linux-kernel@vger.kernel.org>, x86 <x86@kernel.org>, iommu@lists.linux-foundation.org, jacob.jun.pan@intel.com Subject: Re: [PATCH 5/7] x86/mmu: Allocate/free PASID Date: Tue, 28 Apr 2020 20:54:01 +0200 [thread overview] Message-ID: <87tv13o306.fsf@nanos.tec.linutronix.de> (raw) In-Reply-To: <20200428112113.000033bd@intel.com> "Jacob Pan (Jun)" <jacob.jun.pan@intel.com> writes: > On Sun, 26 Apr 2020 16:55:25 +0200 > Thomas Gleixner <tglx@linutronix.de> wrote: >> Fenghua Yu <fenghua.yu@intel.com> writes: >> > The PASID is freed when the process exits (so no need to keep >> > reference counts on how many SVM devices are sharing the PASID). >> >> I'm not buying that. If there is an outstanding request with the PASID >> of a process then tearing down the process address space and freeing >> the PASID (which might be reused) is fundamentally broken. >> > Device driver unbind PASID is tied to FD release. So when a process > exits, FD close causes driver to do the following: > > 1. stops DMA > 2. unbind PASID (clears the PASID entry in IOMMU, flush all TLBs, drain > in flight page requests) Fair enough. Explaining that somewhere might be helpful. > For bare metal SVM, if the last mmdrop always happens after FD release, > we can ensure no outstanding requests at the point of ioasid_free(). > Perhaps this is a wrong assumption? If fd release cleans up then how should there be something in flight at the final mmdrop? > For guest SVM, there will be more users of a PASID. I am also > working on adding refcounting to ioasid. ioasid_free() will not release > the PASID back to the pool until all references are dropped. What does more users mean? >> > + if (mm && mm->context.pasid && !(flags & >> > SVM_FLAG_PRIVATE_PASID)) { >> > + /* >> > + * Once a PASID is allocated for this mm, the PASID >> > + * stays with the mm until the mm is dropped. Reuse >> > + * the PASID which has been already allocated for >> > the >> > + * mm instead of allocating a new one. >> > + */ >> > + ioasid_set_data(mm->context.pasid, svm); >> >> So if the PASID is reused several times for different SVMs then every >> time ioasid_data->private is set to a different SVM. How is that >> supposed to work? >> > For the lifetime of the mm, there is only one PASID. svm_bind/unbind_mm > could happen many times with different private data: intel_svm. > Multiple devices can bind to the same PASID as well. But private data > don't change within the first bind and last unbind. Ok. I read through that spaghetti of intel_svm_bind_mm() again and now I start to get an idea how that is supposed to work. What a mess. That function really wants to be restructured in a way so it is understandable to mere mortals. Thanks, tglx
WARNING: multiple messages have this Message-ID (diff)
From: Thomas Gleixner <tglx@linutronix.de> To: "Jacob Pan \(Jun\)" <jacob.jun.pan@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com>, Tony Luck <tony.luck@intel.com>, Dave Jiang <dave.jiang@intel.com>, Ashok Raj <ashok.raj@intel.com>, Ravi V Shankar <ravi.v.shankar@intel.com>, x86 <x86@kernel.org>, linux-kernel <linux-kernel@vger.kernel.org>, Dave Hansen <dave.hansen@intel.com>, iommu@lists.linux-foundation.org, Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>, jacob.jun.pan@intel.com, H Peter Anvin <hpa@zytor.com>, David Woodhouse <dwmw2@infradead.org> Subject: Re: [PATCH 5/7] x86/mmu: Allocate/free PASID Date: Tue, 28 Apr 2020 20:54:01 +0200 [thread overview] Message-ID: <87tv13o306.fsf@nanos.tec.linutronix.de> (raw) In-Reply-To: <20200428112113.000033bd@intel.com> "Jacob Pan (Jun)" <jacob.jun.pan@intel.com> writes: > On Sun, 26 Apr 2020 16:55:25 +0200 > Thomas Gleixner <tglx@linutronix.de> wrote: >> Fenghua Yu <fenghua.yu@intel.com> writes: >> > The PASID is freed when the process exits (so no need to keep >> > reference counts on how many SVM devices are sharing the PASID). >> >> I'm not buying that. If there is an outstanding request with the PASID >> of a process then tearing down the process address space and freeing >> the PASID (which might be reused) is fundamentally broken. >> > Device driver unbind PASID is tied to FD release. So when a process > exits, FD close causes driver to do the following: > > 1. stops DMA > 2. unbind PASID (clears the PASID entry in IOMMU, flush all TLBs, drain > in flight page requests) Fair enough. Explaining that somewhere might be helpful. > For bare metal SVM, if the last mmdrop always happens after FD release, > we can ensure no outstanding requests at the point of ioasid_free(). > Perhaps this is a wrong assumption? If fd release cleans up then how should there be something in flight at the final mmdrop? > For guest SVM, there will be more users of a PASID. I am also > working on adding refcounting to ioasid. ioasid_free() will not release > the PASID back to the pool until all references are dropped. What does more users mean? >> > + if (mm && mm->context.pasid && !(flags & >> > SVM_FLAG_PRIVATE_PASID)) { >> > + /* >> > + * Once a PASID is allocated for this mm, the PASID >> > + * stays with the mm until the mm is dropped. Reuse >> > + * the PASID which has been already allocated for >> > the >> > + * mm instead of allocating a new one. >> > + */ >> > + ioasid_set_data(mm->context.pasid, svm); >> >> So if the PASID is reused several times for different SVMs then every >> time ioasid_data->private is set to a different SVM. How is that >> supposed to work? >> > For the lifetime of the mm, there is only one PASID. svm_bind/unbind_mm > could happen many times with different private data: intel_svm. > Multiple devices can bind to the same PASID as well. But private data > don't change within the first bind and last unbind. Ok. I read through that spaghetti of intel_svm_bind_mm() again and now I start to get an idea how that is supposed to work. What a mess. That function really wants to be restructured in a way so it is understandable to mere mortals. Thanks, tglx _______________________________________________ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
next prev parent reply other threads:[~2020-04-28 18:54 UTC|newest] Thread overview: 74+ messages / expand[flat|nested] mbox.gz Atom feed top 2020-03-30 19:33 [PATCH 0/7] x86: tag application address space for devices Fenghua Yu 2020-03-30 19:33 ` Fenghua Yu 2020-03-30 19:33 ` [PATCH 1/7] docs: x86: Add a documentation for ENQCMD Fenghua Yu 2020-03-30 19:33 ` Fenghua Yu 2020-04-26 11:02 ` Thomas Gleixner 2020-04-26 11:02 ` Thomas Gleixner 2020-04-27 20:13 ` Fenghua Yu 2020-04-27 20:13 ` Fenghua Yu 2020-03-30 19:33 ` [PATCH 2/7] x86/cpufeatures: Enumerate ENQCMD and ENQCMDS instructions Fenghua Yu 2020-03-30 19:33 ` Fenghua Yu 2020-04-26 11:06 ` Thomas Gleixner 2020-04-26 11:06 ` Thomas Gleixner 2020-04-27 20:17 ` Fenghua Yu 2020-04-27 20:17 ` Fenghua Yu 2020-03-30 19:33 ` [PATCH 3/7] x86/fpu/xstate: Add supervisor PASID state for ENQCMD feature Fenghua Yu 2020-03-30 19:33 ` Fenghua Yu 2020-04-26 11:17 ` Thomas Gleixner 2020-04-26 11:17 ` Thomas Gleixner 2020-04-27 20:33 ` Fenghua Yu 2020-04-27 20:33 ` Fenghua Yu 2020-03-30 19:33 ` [PATCH 4/7] x86/msr-index: Define IA32_PASID MSR Fenghua Yu 2020-03-30 19:33 ` Fenghua Yu 2020-04-26 11:22 ` Thomas Gleixner 2020-04-26 11:22 ` Thomas Gleixner 2020-04-27 20:50 ` Fenghua Yu 2020-04-27 20:50 ` Fenghua Yu 2020-03-30 19:33 ` [PATCH 5/7] x86/mmu: Allocate/free PASID Fenghua Yu 2020-03-30 19:33 ` Fenghua Yu 2020-04-26 14:55 ` Thomas Gleixner 2020-04-26 14:55 ` Thomas Gleixner 2020-04-27 22:18 ` Fenghua Yu 2020-04-27 22:18 ` Fenghua Yu 2020-04-27 23:44 ` Thomas Gleixner 2020-04-27 23:44 ` Thomas Gleixner 2020-04-28 18:21 ` Jacob Pan (Jun) 2020-04-28 18:21 ` Jacob Pan (Jun) 2020-04-28 18:54 ` Thomas Gleixner [this message] 2020-04-28 18:54 ` Thomas Gleixner 2020-04-28 19:07 ` Luck, Tony 2020-04-28 19:07 ` Luck, Tony 2020-04-28 20:42 ` Jacob Pan (Jun) 2020-04-28 20:42 ` Jacob Pan (Jun) 2020-04-28 20:59 ` Luck, Tony 2020-04-28 20:59 ` Luck, Tony 2020-04-28 22:13 ` Jacob Pan (Jun) 2020-04-28 22:13 ` Jacob Pan (Jun) 2020-04-28 22:32 ` Luck, Tony 2020-04-28 22:32 ` Luck, Tony 2020-04-28 20:40 ` Jacob Pan (Jun) 2020-04-28 20:40 ` Jacob Pan (Jun) 2020-04-28 20:57 ` Fenghua Yu 2020-04-28 20:57 ` Fenghua Yu 2020-03-30 19:33 ` [PATCH 6/7] x86/traps: Fix up invalid PASID Fenghua Yu 2020-03-30 19:33 ` Fenghua Yu 2020-04-26 15:25 ` Thomas Gleixner 2020-04-26 15:25 ` Thomas Gleixner 2020-04-27 20:11 ` Fenghua Yu 2020-04-27 20:11 ` Fenghua Yu 2020-04-28 0:13 ` Thomas Gleixner 2020-04-28 0:13 ` Thomas Gleixner 2020-04-27 22:46 ` Raj, Ashok 2020-04-27 22:46 ` Raj, Ashok 2020-04-27 23:08 ` Luck, Tony 2020-04-27 23:08 ` Luck, Tony 2020-04-28 0:20 ` Thomas Gleixner 2020-04-28 0:20 ` Thomas Gleixner 2020-04-28 0:54 ` Thomas Gleixner 2020-04-28 0:54 ` Thomas Gleixner 2020-04-28 1:08 ` Raj, Ashok 2020-04-28 1:08 ` Raj, Ashok 2020-03-30 19:33 ` [PATCH 7/7] x86/process: Clear PASID state for a newly forked/cloned thread Fenghua Yu 2020-03-30 19:33 ` Fenghua Yu 2020-04-22 20:41 ` [PATCH 0/7] x86: tag application address space for devices Fenghua Yu 2020-04-22 20:41 ` Fenghua Yu
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=87tv13o306.fsf@nanos.tec.linutronix.de \ --to=tglx@linutronix.de \ --cc=ashok.raj@intel.com \ --cc=baolu.lu@linux.intel.com \ --cc=bp@alien8.de \ --cc=dave.hansen@intel.com \ --cc=dave.jiang@intel.com \ --cc=dwmw2@infradead.org \ --cc=fenghua.yu@intel.com \ --cc=hpa@zytor.com \ --cc=iommu@lists.linux-foundation.org \ --cc=jacob.jun.pan@intel.com \ --cc=linux-kernel@vger.kernel.org \ --cc=mingo@redhat.com \ --cc=ravi.v.shankar@intel.com \ --cc=sohil.mehta@intel.com \ --cc=tony.luck@intel.com \ --cc=x86@kernel.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.